© 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. 16-GEMMASCOPE-RES-16K
    11. 9594
    Prev
    Next
    INDEX
    Explanations

    instances of significant numerical values and references to legal or formal actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    UrlResolution
    -0.44
    bootstrapcdn
    -0.40
    tock
    -0.37
    ftagPool
    -0.36
    AndEndTag
    -0.36
    ffins
    -0.36
    idue
    -0.36
    ifrance
    -0.35
    VIAF
    -0.35
    ことができました
    -0.35
    POSITIVE LOGITS
    ьаж
    0.50
    BagConstraints
    0.49
     según
    0.48
     مشين
    0.47
    Tikang
    0.47
     என்று
    0.47
     հղումներ
    0.46
    según
    0.46
    Begriffsklä
    0.43
     autant
    0.42
    Activations Density 0.336%

    No Known Activations