© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10616
    Prev
    Next
    INDEX
    Explanations

    comment lines in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.79
    躇
    -0.74
     للمعارف
    -0.73
    contentLoaded
    -0.71
     Bian
    -0.70
    出版年
    -0.68
    Datuak
    -0.67
    postIndex
    -0.66
     MainAxisSize
    -0.66
    PreferredItem
    -0.65
    POSITIVE LOGITS
    //
    1.40
     //
    1.18
    //
    1.09
    {//
    0.91
    );//
    0.91
    ;//
    0.90
    )//
    0.90
     {//
    0.88
    ,//
    0.84
    ){//
    0.83
    Activations Density 0.074%

    No Known Activations