© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1801
    Prev
    Next
    INDEX
    Explanations

    elements and actions related to buttons in code or interfaces

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.64
     ModelExpression
    -0.59
    aarrggbb
    -0.58
     }}"></
    -0.57
    ########.
    -0.56
    euvres
    -0.54
    Diwedd
    -0.51
    paio
    -0.50
    curacy
    -0.50
     '\\;'
    -0.48
    POSITIVE LOGITS
     button
    2.74
    button
    2.35
     buttons
    2.30
     Button
    2.25
    Button
    2.19
     BUTTON
    2.10
    BUTTON
    1.92
    按钮
    1.91
     Buttons
    1.85
    ボタン
    1.81
    Activations Density 0.192%

    No Known Activations