© 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. 21-GEMMASCOPE-RES-16K
    11. 10530
    Prev
    Next
    INDEX
    Explanations

    various descriptions and metadata elements in structured documents

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     onResponse
    -0.54
     &___
    -0.52
    findpost
    -0.49
    pant
    -0.46
     OnTrigger
    -0.45
    Gemeinden
    -0.43
    pump
    -0.43
    DEAL
    -0.43
    tubes
    -0.43
    galvan
    -0.43
    POSITIVE LOGITS
     description
    0.76
    description
    0.69
     descripción
    0.66
     descrição
    0.63
     explanation
    0.63
     descrizione
    0.62
    Description
    0.60
     descriptions
    0.59
     explanations
    0.58
     설명
    0.58
    Activations Density 0.307%

    No Known Activations