© 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. 101119
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <eos>
    -0.41
    2
    -0.39
    ,
    -0.38
     
    -0.36
     bil
    -0.34
     inter
    -0.34
     proof
    -0.33
     e
    -0.33
    ↵↵
    -0.33
     E
    -0.33
    POSITIVE LOGITS
    ftagPool
    8.75
    tagPool
    2.86
     '\\;'
    1.68
     autorytatywna
    1.27
    jspx
    1.27
    fjspx
    1.26
    SequentialGroup
    1.23
    tagHelperRunner
    1.12
    RenderAtEndOf
    1.10
    bootstrapcdn
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.