© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 9823
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remember" and its variations, indicating a focus on memory and recall

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     OFDb
    -0.75
    ofern
    -0.74
    KommentareTeilen
    -0.72
     roulant
    -0.70
     MongoClient
    -0.69
    URLException
    -0.67
     ajuns
    -0.67
    Искәрмәләр
    -0.67
    niająca
    -0.67
     Obrador
    -0.66
    POSITIVE LOGITS
     how
    0.82
     fondly
    0.73
     what
    0.62
     why
    0.61
    Remember
    0.61
    ance
    0.61
     Remember
    0.60
     remember
    0.59
     remembers
    0.58
     about
    0.55
    Activations Density 0.060%

    No Known Activations