© 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. 7-GEMMASCOPE-RES-16K
    11. 12378
    Prev
    Next
    INDEX
    Explanations

    phrases relating to roles, actions, and identifiers within a narrative context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    @[+][
    -0.31
     composição
    -0.29
    ..
    -0.29
     compreensão
    -0.29
    Luckily
    -0.28
     consciência
    -0.28
     however
    -0.28
     agência
    -0.28
    and
    -0.28
    -------------
    -0.28
    POSITIVE LOGITS
    tagHelperRunner
    0.94
     autorytatywna
    0.80
    TagMode
    0.78
    RectangleBorder
    0.77
    AndEndTag
    0.76
    expandindo
    0.74
    abestanden
    0.69
    ########.
    0.68
     виправивши
    0.67
     contextLoads
    0.66
    Activations Density 1.031%

    No Known Activations