© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 48976
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses related to specific websites

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    IsMutable
    -0.71
     Exactos
    -0.59
    ItemBackground
    -0.57
    WriteAttribute
    -0.49
    elemField
    -0.47
    MessageOf
    -0.46
     Hälfte
    -0.46
     especiais
    -0.44
     Exacts
    -0.44
    astéroïdes
    -0.43
    POSITIVE LOGITS
    crawl
    2.50
    mud
    1.52
    Crawl
    1.45
     crawl
    1.43
     Crawl
    1.41
    craw
    1.23
    Mud
    1.15
     mud
    1.13
    MUD
    1.09
     crawls
    1.09
    Activations Density 0.000%

    No Known Activations