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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6199
    Prev
    Next
    INDEX
    Explanations

    variable assignments and declarations in code

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

    Code blocks containing "tracing" or "=" signs

    np_acts-logits-general · gemini-2.0-flash

    tracing.IsEnabled()

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.93
     للمعارف
    -0.76
     Италијани
    -0.73
    msgTypes
    -0.69
    TypedDataSet
    -0.69
     Normdatei
    -0.68
    errHandler
    -0.65
    MigrationBuilder
    -0.65
    InjectAttribute
    -0.63
    endpush
    -0.63
    POSITIVE LOGITS
     =
    0.42
     aikana
    0.35
     started
    0.35
     neither
    0.33
    หมือน
    0.33
     joined
    0.33
     still
    0.33
     suspensión
    0.32
     esclavos
    0.32
     suiv
    0.31
    Activations Density 0.212%

    No Known Activations