© 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. 10398
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or terms, often involving operations with variables

    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
    MigrationBuilder
    -0.77
    setVerticalGroup
    -0.64
    ValueStyle
    -0.63
     يتيمه
    -0.62
    RenderAtEndOf
    -0.61
     queſta
    -0.60
    balleur
    -0.57
     resourceCulture
    -0.56
    expandindo
    -0.55
     increí
    -0.54
    POSITIVE LOGITS
     …
    0.39
     ...
    0.39
    <eos>
    0.39
     Barton
    0.38
     Hur
    0.37
     dem
    0.35
     Bill
    0.35
    랑
    0.35
     static
    0.34
     Chart
    0.34
    Activations Density 0.743%

    No Known Activations