© 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. 116714
    Prev
    Next
    INDEX
    Explanations

    relationships and structures in formal and scientific contexts

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

    structure, shape, style, properties

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     onOptions
    -0.73
    RenderAtEndOf
    -0.67
    parsedMessage
    -0.67
    enderror
    -0.66
    awtextra
    -0.65
    httphttps
    -0.65
    ⟬
    -0.64
     sumpay
    -0.61
    PerformLayout
    -0.60
     ***!
    -0.60
    POSITIVE LOGITS
     similar
    0.35
    try
    0.33
    similar
    0.33
     ähn
    0.31
     identical
    0.31
    Referanser
    0.30
     liknande
    0.30
     những
    0.29
    基本的に
    0.29
    <eos>
    0.29
    Activations Density 0.071%

    No Known Activations