© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6947
    Prev
    Next
    INDEX
    Explanations

    concepts related to evolutionary biology and genetic diversity

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

    technical and scientific language in academic or research contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ſcher
    -0.73
    WireFormatLite
    -0.68
     समीक्षाओं
    -0.65
     للاسماء
    -0.64
    ThroughAttribute
    -0.63
     unknownFields
    -0.63
     müſſen
    -0.62
    colhead
    -0.62
    iſen
    -0.60
    cookieParser
    -0.60
    POSITIVE LOGITS
     mechanism
    0.76
     mechanisms
    0.70
     phénomènes
    0.66
     occurs
    0.63
     phenomenon
    0.60
     phenomena
    0.60
     occurring
    0.57
     occur
    0.57
     mécanisme
    0.55
     mecanismos
    0.54
    Activations Density 1.392%

    No Known Activations