© 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. 31-GEMMASCOPE-RES-131K
    11. 15978
    Prev
    Next
    INDEX
    Explanations

    numerical values, often likely representing statistical data or metrics

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

    formatting numerical data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beliebtesten
    -0.32
    waitKey
    -0.30
    NegativeButton
    -0.29
    Read
    -0.28
    readObject
    -0.28
     birbir
    -0.28
     wichtigsten
    -0.27
    Descubre
    -0.26
    fillColor
    -0.26
    Sonstiges
    -0.26
    POSITIVE LOGITS
     format
    0.94
     formatting
    0.91
     formats
    0.88
     formatted
    0.85
     Format
    0.79
     Formats
    0.78
    格式
    0.77
     للاسماء
    0.77
     formato
    0.76
    format
    0.74
    Activations Density 0.118%

    No Known Activations