© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21508
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming comments and documentation formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    omitempty
    -0.69
    tagext
    -0.67
     Wikimedijinoj
    -0.66
    ThroughAttribute
    -0.66
     незавершена
    -0.64
    -------
    -0.62
    migrationBuilder
    -0.62
    richTextPanel
    -0.60
     Chwiliwch
    -0.60
     ModelExpression
    -0.60
    POSITIVE LOGITS
    charis
    0.36
     Fla
    0.35
     Resource
    0.34
     lectured
    0.33
    chenken
    0.33
    case
    0.33
     Adam
    0.32
    glers
    0.32
    adam
    0.31
     Practical
    0.31
    Activations Density 0.039%

    No Known Activations