© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3632
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to form submission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    UI buttons or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostavi
    -0.43
     pend
    -0.42
     Haftung
    -0.42
     vom
    -0.41
    सत
    -0.40
    ISL
    -0.40
    ACHI
    -0.39
    воро
    -0.39
    ilang
    -0.38
    ケイ
    -0.38
    POSITIVE LOGITS
     button
    1.45
     buttons
    1.33
    Button
    1.31
     BUTTON
    1.30
     Button
    1.28
    button
    1.27
     Buttons
    1.19
    JButton
    1.18
    ボタン
    1.11
    BUTTON
    1.11
    Activations Density 0.131%

    No Known Activations