© 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. 3120
    Prev
    Next
    INDEX
    Explanations

    specific dates and numerical references within the text

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

    four-digit years in date ranges or specific time periods.

    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
     تضيفلها
    -0.71
     AssemblyTitle
    -0.68
    WriteTagHelper
    -0.60
     ExecuteAsync
    -0.58
    httphttps
    -0.57
    帖最后由
    -0.56
     CreateTagHelper
    -0.53
    NUMX
    -0.52
    ChildScrollView
    -0.52
     متعلقه
    -0.52
    POSITIVE LOGITS
    –
    0.77
     until
    0.73
     až
    0.72
     đến
    0.71
     till
    0.69
     hingga
    0.68
     hasta
    0.66
    至
    0.66
     hanggang
    0.65
     –
    0.63
    Activations Density 0.470%

    No Known Activations