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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9376
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts related to the action of knocking

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

    and sounds like "knock."

    np_acts-logits-general · gemini-2.0-flash

    knock or strike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FSC
    -0.35
    Kari
    -0.33
    cún
    -0.32
    WEBPACK
    -0.31
     rootReducer
    -0.31
     Hijo
    -0.31
     vPvB
    -0.30
     kiện
    -0.30
    茅
    -0.30
    engeti
    -0.29
    POSITIVE LOGITS
     knock
    1.83
    knock
    1.64
     Knock
    1.64
     knocking
    1.63
     knocks
    1.62
    Knock
    1.57
     knocked
    1.56
    kno
    1.24
    Kno
    1.22
     Kno
    1.21
    Activations Density 0.155%

    No Known Activations