© 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. 36-GEMMASCOPE-RES-16K
    11. 4851
    Prev
    Next
    INDEX
    Explanations

    content related to informative articles and guides

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     nahilalakip
    -0.60
    OrNil
    -0.53
    NamedQueries
    -0.53
    Cyfeiriadau
    -0.52
     Beobachtung
    -0.47
     actionPerformed
    -0.47
     województwie
    -0.45
    leşti
    -0.45
     Meksiku
    -0.44
     refuser
    -0.44
    POSITIVE LOGITS
     explain
    1.41
     outlining
    1.36
     outlines
    1.34
     outline
    1.32
     explaining
    1.27
     detailing
    1.22
     explains
    1.22
     describe
    1.20
     outlined
    1.16
     explained
    1.11
    Activations Density 0.962%

    No Known Activations