© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3064
    Prev
    Next
    INDEX
    Explanations

    symbols and structures commonly used in programming and mathematical notation

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

    technical or scientific notation, mathematical symbols, and statistical/computational variables.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    formal technical/scientific notation, including mathematical symbols and subscripts, numeric types and code-like tokens, and variable/parameter names in equations or data tables.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    numeric values and mathematical notation in technical or scientific code and documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Signalez
    -0.51
    layoutControl
    -0.51
    GTCX
    -0.45
    endpush
    -0.45
    ArgsConstructor
    -0.44
     Eindruck
    -0.41
    PageRoute
    -0.41
    ListItemIcon
    -0.41
     RouterModule
    -0.40
    accompag
    -0.40
    POSITIVE LOGITS
    InitStruct
    0.46
    ScopeManager
    0.45
    μβρίου
    0.44
    contentLoaded
    0.44
    wargs
    0.43
     ब्रेकडाउन
    0.42
    yntaxException
    0.41
     समीक्षाओं
    0.40
     चीज़ों
    0.40
     архивлан
    0.38
    Activations Density 0.295%

    No Known Activations