© 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. 31-GEMMASCOPE-RES-131K
    11. 111183
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "and."

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

    connecting words in pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     similar
    -0.46
    パル
    -0.35
    elif
    -0.35
     suitable
    -0.32
    similar
    -0.31
     vs
    -0.31
     similaires
    -0.31
    tischer
    -0.31
    上有
    -0.30
     a
    -0.30
    POSITIVE LOGITS
    Personendaten
    0.82
    LookAnd
    0.81
    webElementXpaths
    0.77
     ProtoMessage
    0.76
    majority
    0.73
     betweenstory
    0.72
    AccessorTable
    0.69
    ConstraintMaker
    0.69
    HideFlags
    0.68
    parsedMessage
    0.66
    Activations Density 0.185%

    No Known Activations