© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4325
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to scientific measurements and analyses

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

    The neuron activates on statistical measurements, quantitative values, and numerical data analysis in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical scientific and medical measurement values and quantities.

    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
     HasFactory
    -0.46
     FetchType
    -0.45
    oredCriteria
    -0.44
    oa̍t
    -0.41
    Flora
    -0.40
    Välislingid
    -0.39
     ligiloj
    -0.39
     horarios
    -0.38
    pricing
    -0.38
    Expensive
    -0.38
    POSITIVE LOGITS
     total
    1.03
     overall
    0.84
     estimated
    0.78
     actual
    0.73
    total
    0.72
     absolute
    0.71
     predicted
    0.70
     theoretical
    0.70
     maximum
    0.69
    overall
    0.69
    Activations Density 1.487%

    No Known Activations