© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 348
    Prev
    Next
    INDEX
    Explanations

    function calls and method definitions in code

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

    occurrences of function calls and parentheses in programming syntax

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

    code with function definitions and return values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ます
    -0.70
    mens
    -0.68
    置
    -0.63
    a
    -0.63
    ical
    -0.62
     Zie
    -0.62
    5
    -0.60
     Lacey
    -0.59
    O
    -0.59
    naeus
    -0.59
    POSITIVE LOGITS
     للمعارف
    0.90
    |}{\
    0.87
    queryInterface
    0.86
    atemala
    0.85
     NDEBUG
    0.83
    GEBURTSDATUM
    0.81
    }(),
    0.78
    RetentionPolicy
    0.78
     calldata
    0.76
    PyExc
    0.76
    Activations Density 0.084%

    No Known Activations