© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 77255
    Prev
    Next
    INDEX
    Explanations

    words and phrases that signify evaluation, judgment, or contribution in various contexts

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

    adversely affect, widely viewed, closely associated

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    <b>
    -0.35
     Com
    -0.33
    <strong>
    -0.32
    src
    -0.30
     Pal
    -0.29
    },{
    -0.29
    Source
    -0.29
     no
    -0.29
    ില
    -0.28
     
    -0.28
    POSITIVE LOGITS
    bootstrapcdn
    1.00
     MainAxisSize
    0.96
    MigrationBuilder
    0.95
    ьаж
    0.90
    ActionCreators
    0.87
     GenerationType
    0.85
    MemoryWarning
    0.84
    BindingResult
    0.84
    styleType
    0.82
    AndEndTag
    0.82
    Activations Density 0.097%

    No Known Activations