© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5917
    Prev
    Next
    INDEX
    Explanations

    numerical values related to quantities and measurements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    numbers describing quantities, especially when written out as words (like "one hundred and twenty" or "thirty-five").

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    s
    -0.54
    ing
    -0.52
    存于互联网档案馆
    -0.42
    참고
    -0.41
     tremor
    -0.41
    ︎
    -0.41
    n
    -0.41
    Попис
    -0.40
    gcp
    -0.40
    mailto
    -0.40
    POSITIVE LOGITS
     twenty
    1.34
     ninety
    1.27
     seventy
    1.27
     thirty
    1.27
     sixty
    1.23
     eighty
    1.23
     fifty
    1.23
     forty
    1.23
    twenty
    1.21
     TWENTY
    1.12
    Activations Density 0.189%

    No Known Activations