© 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. 39849
    Prev
    Next
    INDEX
    Explanations

    relationships and correlations between variables in a dataset

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

    quantifying relationships between pairs

    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
    $_['
    -0.56
    Hentet
    -0.55
     Normdatei
    -0.51
    inghouse
    -0.50
    addPreferredGap
    -0.50
    endpush
    -0.49
    #
    -0.49
     GridLayout
    -0.48
    RenderAtEndOf
    -0.48
    AccessFile
    -0.47
    POSITIVE LOGITS
     pairs
    2.44
     pair
    2.17
    pairs
    1.94
     Pairs
    1.90
    pair
    1.88
     Pair
    1.84
     paire
    1.77
    Pairs
    1.77
    Pair
    1.76
     pairings
    1.61
    Activations Density 0.337%

    No Known Activations