© 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. 53171
    Prev
    Next
    INDEX
    Explanations

    references to static properties and methods in programming contexts

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

    static methods and variables

    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
     sindaco
    -0.42
     ympä
    -0.39
     coast
    -0.36
     fracaso
    -0.36
    为止
    -0.36
     riego
    -0.36
     flexível
    -0.36
     lendemain
    -0.36
    üyor
    -0.36
    addContainerGap
    -0.36
    POSITIVE LOGITS
    staticmethod
    0.83
    JvmStatic
    0.82
     linkovi
    0.66
    Static
    0.59
     Administrativna
    0.57
     Static
    0.57
    internalType
    0.57
    statics
    0.56
    isStatic
    0.56
     STATIC
    0.54
    Activations Density 0.019%

    No Known Activations