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

    Neuronpedia

    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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 64028
    Prev
    Next
    INDEX
    Explanations

    interrogative and imperative expressions, often used in questions or requests

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

    foreign language and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens at the start of a reply or new answer/turn (turn-initial or sentence-initial tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    tagHelperRunner
    -0.94
    offsetof
    -0.73
    ResumeLayout
    -0.70
     defaultstate
    -0.69
     estekak
    -0.69
    setViewportView
    -0.68
    aarrggbb
    -0.67
    OGND
    -0.65
    enderror
    -0.64
    IsMutable
    -0.64
    POSITIVE LOGITS
    ulang
    0.33
     chegou
    0.29
     εί
    0.29
     Kriege
    0.28
    stalt
    0.27
    ẫ
    0.27
    wał
    0.27
    Time
    0.27
     ActivatedRoute
    0.26
     mult
    0.26
    Activations Density 0.000%

    No Known Activations