© 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. 31-GEMMASCOPE-RES-16K
    11. 3159
    Prev
    Next
    INDEX
    Explanations

    terms related to multiculturalism and diversity in various sectors, including demographics and market dynamics

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

    technical and domain-specific nouns related to specialized fields.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
    人了
    -0.55
    .
    -0.48
    .\\
    -0.44
    ².
    -0.43
    ``.
    -0.43
    ³.
    -0.42
    `.
    -0.41
    ."""
    -0.41
     {}'.
    -0.40
    .");
    -0.40
    POSITIVE LOGITS
    들은
    0.82
     bowiem
    0.81
     infatti
    0.81
     inilah
    0.81
     EconPapers
    0.80
     totiž
    0.75
    그는
    0.73
     azonban
    0.69
    리는
    0.68
     inoltre
    0.68
    Activations Density 1.828%

    No Known Activations