Twenty-five participants (14 females, 11 males; 18–27 years old) participated in this study. All participants were right handed, native Dutch speakers and had no history of neurological or psychiatric disorders including dyslexia (based on self reports). Datasets from two subjects were excluded from the analysis because of excessive head movements.

This study is approved by the ethical committee (Comissie Mens Gebonden Onderzoek Regio Arnhem-Nijmegen). Subjects gave written informed consent to participate in this study.

The task contained 35 (or 29) blocks and each block had three parts. Below, we will explain the criteria used to decide which version (35 or 29 blocks) was chosen. Each block started with 9 (or 11) LTM encoding trials, followed by 6 (or 7) WM maintenance trials and ended with 9 (or 11) LTM retrieval trials (Figure 1A). In LTM encoding and WM maintenance trials, three words were presented (600 ms/word) followed by a 3400 ms rehearsal interval (Figure 1B). Each word was used only once in the task (for a detailed description of the stimuli see [20]).

During the LTM encoding trials subjects were instructed to encode the order of the words in the triplet during the 3.4 s rehearsal interval. Subjects were aware that they would be asked to reproduce the word order later. The subjects' ability to immediately reproduce the word order in the triplets was tested in 20% of the trials (this was only done to make the LTM encoding part equal to the WM part). Trials followed by a test were excluded from the analysis.

During the WM maintenance trials, the presented word-triplet was to be maintained for 3.4 s. The triplets were composed of three different words (load three) or one word repeated three times (load one). Subjects' ability to reproduce the word order in the triplets was tested in 20% of the trials. For load-one trials, the same or a lure word was shown three times and subjects were asked to give a “match/no match” response. Trials followed by a test were excluded from the analysis.

During LTM retrieval trials, participants were asked to reconstruct the order of the words in the triplets they learned in the encoding part of the same block (Figure 1C). Every word was represented by a button. By pressing the buttons in the right order, subjects had to reproduce the learned sequences. Additionally, 20% catch trials were included in the retrieval part in which one of the words was replaced by a word not belonging to the triplet. When noticing these trials, participants had to press button 4.

To ensure an appropriate balance between the number of later remembered and forgotten trials for every subject, two versions of the experiment were made. One version contained 9 LTM sequences per block and 35 blocks in total, the other 11 LTM sequences per block and 29 blocks in total. As determined by their performance during the training session, six participants performed the 11-sequence task and the remaining 19 subjects the 9-sequence task. We aimed to get approximately 70% correctly retrieved sequences for each participant. After analyzing the data we checked whether the two groups of subjects showed similar effects in the gamma and beta band and that was indeed the case.

Participants visited the laboratory two times at successive days. The task was explained and practiced on the first day. To keep the encoding strategies similar for every subject, we encouraged subjects to construct sentences using the three words in each triplet.

On the second day the subjects performed the task in the MEG. Brain activity was recorded with a 275 axial gradiometer MEG system (VSM/CTF systems, Port Coquitlam, Canada) in supine position. The data were sampled at 1200 Hz and low pass filtered at ∼250 Hz. In addition, the horizontal and vertical electrooculograms (EOGs) were recorded to remove the effects of eye movements and blinks later during the offline preprocessing. The electrocardiogram (ECG) was recorded to be able to remove cardiac artefacts from the data. Head position was monitored using three coils placed at the nasion and in both ear canals. The recording session lasted approximately two hours including a 15 minute break. After the MEG recordings, a questionnaire was administered to evaluate whether participants applied the strategy provided in the instructions.

Finally, an anatomical MRI scan was acquired using a 1.5T (Siemens, Magnetom Avanto) or a 3T (Siemens, Magnetom Trio) MRI scanner. Ear plugs containing oil with vitamin E were placed in the ear canals during MRI acquisition enabling us to realign the MEG source reconstructions and the subject specific structural MRI data.

The MEG data were analyzed using Fieldtrip; a Matlab toolbox developed at the Donders Institute for Brain, Cognition and Behaviour (website: http://www.ru.nl/neuroimaging/fieldtrip). Trials contaminated with muscle or SQUID artefacts were rejected. The data was down-sampled to 600 Hz after applying a 150 Hz low pass filter. Eye and heart beat artefacts were removed from the data using independent component analysis (ICA). On average, the LTM remembered, LTM forgotten, WM load 3 and WM load 1 conditions contained 186 (range: 123–242), 107 (range: 50–170), 95 (range: 81–103) and 94 (range: 73–105) trials, respectively.

Time-frequency representations of power (TFRs; 4–32 Hz and 50–120 Hz) based on a sliding time window (steps of 50 ms) were computed from data segments recorded during presentation of the words (2.2 s) and the rehearsal interval (3.4 s). Power values for horizontal and vertical components of the planar gradients were calculated and summed for each sensor using signals from the neighbouring sensors, thereby approximating the signal measured by MEG systems with planar gradiometers [21]. For the lower frequencies (4–32 Hz), we used an adaptive time window containing 4 cycles (i.e. ΔT = 4/f) and applied a Hanning taper resulting in adaptive spectral smoothing of Δf∼1/ΔT. A fixed time window of 200 ms is used to analyze the high frequency oscillations (50–120 Hz) in the data. We used three orthogonal Slepian tapers which resulted in a spectral smoothing of ∼10 Hz. Absolute differences of average power estimates across tapers between conditions are reported. Note that the power estimates are not baseline corrected. This is not needed since power values are absolute measures. Also, the task had a blocked design and therefore different difficulty-expectancies for the LTM and WM conditions could have caused differences in the baselines.

A beamforming approach using an adaptive filtering technique (Dynamic Imaging of Coherent Sources, DICS) was applied to the data to identify the sources of the oscillatory activity [22]. This spatial filter is constructed from the cross-spectral density matrix and the lead field matrix. It passes activity optimally from the location of interest while attenuating all other activity in the data. Cross-spectral density matrices were obtained from the Fourier transformed data for both LTM and WM trials during the rehearsal interval. The subjects' lead field matrices were calculated from a realistically shaped single-shell description of the brain based on the individual anatomical MRI [23]. A similar head model was constructed from a template MRI. The subject specific and template head models in MNI (Montreal Neurological Institute) coordinates were divided into regular 1 cm three-dimensional grids. Each individual's MRI was warped to the template MRI using SPM2 (http://www.fil.ion.ucl.ac.uk/spm) and the inverse of that warp was applied to the template grid. Because of this warping, a specific grid point is located at the same structural location in the template MRI and the subject specific anatomical MRIs. After applying the spatial filter to the data, the relative difference between the average power estimates of the two conditions was overlaid on the participants' MRI. Note that, for the source reconstruction, we used the data from the axial sensors and not the planar gradients.

We applied statistical tests to the −1.7–0.0 s interval in which the words were presented and the 0.0–3.0 s interval in which subjects rehearsed the order of the words (t = 0 s indicates the start of rehearsal interval). A non-parametric cluster-based randomization test was applied to the sensor and source level data [24]. This test controls for type 1 errors in situations involving multiple comparisons by clustering neighbouring channels or grid points which show the same effect. If the t-value at a sensor/grid point exceeded a threshold (p<0.05) these sensors/grid points were included in a cluster. The cluster-level statistic of each cluster was defined as the sum of the t-values of all sensors/grid points in the cluster. The cluster with the maximum summed t-values was used as a test statistic and compared to the randomization null-distribution. To make the randomization null-distribution, per participant averages for both conditions were randomly divided in two groups and the maximum cluster-level statistics were calculated. This procedure was repeated for 500 times.

Triplets encoded in LTM were retrieved successfully in 64.6±10.2% of the trials (chance level = 16.6%). For WM load 3 and WM load 1 trials, subjects responded correctly in 91.6±7.2% and 97.3±4.0% of the trials, respectively. When evaluating which strategies subjects used, they reported to have used a rote rehearsal or no strategy for the WM trials (10 and 8 participants, respectively). During LTM trials, subjects often made sentences or had a combined visual and sentence making strategy (16 and 6 participants, respectively).

Time-frequency representations (TFRs) of power were calculated for the rehearsal interval of LTM and WM trials. Comparing the oscillatory activity in these two trial types revealed a robust difference in gamma power (55–65 Hz) over left central sensors which was stronger in LTM encoding trials (p<0.0001, 0.0–3.0 s) (significant sensors are marked in Figure 2A). The change in gamma activity was sustained during the full rehearsal interval. A beamforming analysis was applied to identify the source of the difference in gamma power. The source appeared strongest over the medial part of left BA6 including large parts of the supplementary motor area (SMA) and pre-SMA. Figure 2B shows the positive z-values found when comparing relative difference in gamma power (55–65 Hz) between LTM and WM trials per grid point (p<0.0001). The average power obtained in the same analysis is shown in Figure 2C (threshold at half of the maximum). When performing time-frequency analysis on the data recorded during presentation of the words, we noticed that the difference in gamma power emerges even before the rehearsal interval begins (p<0.0001, −1.7–0.0 s). Figure 2D shows the temporal development of gamma power (55–65 Hz) during word presentation and the rehearsal interval for the sensors in the significant cluster (which are marked in Figure 2A).

Next, we investigated the subsequent memory effect during the rehearsal interval. The trials from the LTM encoding part were divided in two groups; triplets that were correctly and incorrectly reproduced during LTM retrieval trials (‘later remembered’ and ‘later forgotten’ trials, respectively). We observed an increase of fronto-central gamma band activity when comparing the activity for these two conditions (Figure 3). When applying a cluster based randomization test including all sensors, there was a weak trend (55–65 Hz, 0.0–3.0 s, p = 0.19). When we constrained the statistical comparison to the first half of the rehearsal interval and included only sensors in the significant cluster found when comparing LTM and WM trials, the subsequent memory effect was significant (p = 0.032). Like the difference in gamma activity between LTM and WM trials, this effect started to emerge at the end of the word presentation period (see Figure 2D). When considering the topography of the subsequent memory effect (Figure 3) differences over posterior regions and right frontal areas can be observed. Normalizing the difference with the variance (z-values) shows that these effects are driven by a few subjects and not strong enough to be significant on the whole group level.

Next, TFRs where calculated for lower frequencies (4–32 Hz). Results in the alpha band have already been reported in Meeuwissen et al. (2010) [20]. During the rehearsal interval beta power over anterior regions was significantly lower for LTM trials compared to WM trials (15–27 Hz, 0.0–3.0, p<0.0001) (Figure 4A). To find the dominant source of this effect, we applied a beamforming approach (Figure 4B,C). The relative difference in source level power was subjected to a cluster-randomization procedure (p<0.0001). Figure 4B shows the negative z-values projected to the brain surface. The effect is widespread but significant in left inferior frontal gyrus (LIFG) and the left insula (Figure 4C). When examining the time courses of beta power at significant sensors (which are marked in Figure 4A) for all conditions it becomes clear that beta power decreased with each word that was presented but was quite constant in the rehearsal period (Figure 4D). Besides a decrease in beta power at anterior sensors when comparing the rehearsal intervals in LTM and WM trials, we found a significant power increase in the beta band at posterior sensors (p = 0.004, Figure 4A).

To substantiate that the gamma and beta modulations were related to processes important for memory encoding, we correlated the power changes with memory performance over subjects. The relative differences in gamma (55–65 Hz, 0.0–3.0 s) and beta power (15–27 Hz, 0.0–3.0 s) at sensors where the effect was significantly different between the LTM encoding and WM maintenance conditions (LTM−WM/LTM+WM) were calculated for all subjects and correlated to the hit rate on LTM trials. The gamma modulation correlated positively with the performance (r = 0.56, p = 0.006, Figure 2E) whereas the beta modulation correlated negatively with performance (r = −0.52, p = 0.011, Figure 4E). Next we correlated the beta and gamma power modulations directly with each other. We found a significant negative correlation (p = 0.022, r = −0.48, Figure 5). In sum, these findings show that individuals who are better at encoding the word sequences in LTM, are also individuals with larger power differences in the gamma and beta band when comparing LTM and WM trials.