© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104969
    Prev
    Next
    INDEX
    Explanations

    references to form elements and their attributes in HTML code

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     للاسماء
    -0.86
     pinulongan
    -0.74
    parsedMessage
    -0.73
     ब्रेकडाउन
    -0.71
    出版年
    -0.71
     Bewußt
    -0.71
     Autorizaciones
    -0.70
     indígen
    -0.68
    writeFieldEnd
    -0.68
    tagHelperRunner
    -0.68
    POSITIVE LOGITS
    -
    0.55
      
    0.41
    ↵
    0.38
     ordinary
    0.38
     R
    0.37
     F
    0.37
     linear
    0.36
     legal
    0.36
     formal
    0.36
     
    0.36
    Activations Density 0.001%

    No Known Activations