© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 70048
    Prev
    Next
    INDEX
    Explanations

    requests for user interaction or assistance

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

    Please + action verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Билгалдахарш
    -0.60
    itinéraire
    -0.58
    ScopeManager
    -0.55
    ItemBackground
    -0.54
    exitRule
    -0.48
    UIControlState
    -0.47
    OrWhiteSpace
    -0.47
     '{@
    -0.47
    ViewImports
    -0.46
    multirow
    -0.46
    POSITIVE LOGITS
    Please
    0.73
     Please
    0.71
     please
    0.71
    please
    0.63
     PLEASE
    0.57
    PLEASE
    0.56
     Bitte
    0.44
    请
    0.43
     Kindly
    0.43
    请选择
    0.43
    Activations Density 0.018%

    No Known Activations