© 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. 30-GEMMASCOPE-RES-16K
    11. 10622
    Prev
    Next
    INDEX
    Explanations

    instances of programming structures and syntax related to code execution

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

    Code, math, and file paths

    np_acts-logits-general · gemini-2.0-flash

    DOI identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    msgTypes
    -0.73
    AndEndTag
    -0.69
    AddHtmlAttribute
    -0.69
    TagMode
    -0.67
    featureID
    -0.65
    +#+
    -0.65
    .",
    -0.64
    migrationBuilder
    -0.62
    astify
    -0.62
    ."],
    -0.61
    POSITIVE LOGITS
    occuper
    0.39
    agissait
    0.36
    ↵
    0.35
     táctil
    0.33
     kvinder
    0.33
    同じく
    0.31
     Gubernur
    0.30
     arbejds
    0.30
    zelfde
    0.30
     provisoire
    0.29
    Activations Density 0.574%

    No Known Activations