© 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. 56155
    Prev
    Next
    INDEX
    Explanations

    instances of quoted text or specific references to challenges and exercises in problem-solving contexts

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

    legal, mathematical, or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    tonode
    -0.60
    RTLR
    -0.56
    GTCX
    -0.55
     صوتيه
    -0.49
     Chwiliwch
    -0.49
    IntoConstraints
    -0.48
    NameInMap
    -0.48
     بيها
    -0.46
    protoimpl
    -0.45
     للاسماء
    -0.45
    POSITIVE LOGITS
    WebControls
    0.41
    TintMode
    0.40
     Artificial
    0.39
    AllAfrica
    0.38
    endmodule
    0.37
    Karriere
    0.36
    __((
    0.35
    RegressionTest
    0.35
    artificial
    0.35
     Transfermarkt
    0.34
    Activations Density 0.005%

    No Known Activations