© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 24250
    Prev
    Next
    INDEX
    Explanations

    references to butterfly species and their characteristics

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

    butterfly descriptions

    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
    AndEndTag
    -0.82
     Wikimedijinoj
    -0.68
    ंदीखरीदारी
    -0.67
     للاسماء
    -0.67
    RegressionTest
    -0.66
     nahilalakip
    -0.65
     gynhyrchwyd
    -0.63
    atchewan
    -0.61
    GraphicsUnit
    -0.60
    点此举报
    -0.59
    POSITIVE LOGITS
     butterfly
    0.98
     butterflies
    0.90
     Butterflies
    0.76
     Butterfly
    0.75
    butterfly
    0.74
    Butterfly
    0.73
    🦋
    0.65
     caterpillars
    0.61
     borboleta
    0.58
    蝴蝶
    0.56
    Activations Density 0.038%

    No Known Activations