Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 42413
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence terminators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    İstinadlar
    -0.33
    prepareStatement
    -0.33
    �
    -0.33
    FunctionFlags
    -0.32
    :✨
    -0.31
     للاسماء
    -0.31
    例文帳に追加
    -0.30
    impl
    -0.30
     "^
    -0.30
     capita
    -0.30
    POSITIVE LOGITS
    erintah
    0.62
    Toast
    0.56
    CloseOperation
    0.52
     Infór
    0.52
    دانشنامهٔ
    0.51
     dezelve
    0.50
     eletrônico
    0.50
     zoude
    0.50
     stanga
    0.50
     poichè
    0.49
    Activations Density 0.000%

    No Known Activations