© 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. 32210
    Prev
    Next
    INDEX
    Explanations

    requests for ideas, suggestions, or advice

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

    asking for ideas or suggestions

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

    It detects direct requests for help or suggestions—short phrases where the author explicitly asks for ideas or advice.

    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
    bootstrapcdn
    -0.51
    lgari
    -0.48
    mappedBy
    -0.47
     queſta
    -0.46
    userManager
    -0.44
    ########.
    -0.42
     ModelExpression
    -0.42
     Mouth
    -0.42
    extAlignment
    -0.39
    IBarButtonItem
    -0.38
    POSITIVE LOGITS
     suggestions
    0.51
     initComponents
    0.50
     informée
    0.50
     Empfehlung
    0.49
     tavsiye
    0.49
     recommends
    0.48
    SharedCtor
    0.48
    AccessorTable
    0.48
     ADVICE
    0.48
     guesses
    0.47
    Activations Density 0.014%

    No Known Activations