© 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. 13-GEMMASCOPE-RES-16K
    11. 11617
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases indicating contrast or clarification

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Major
    -0.45
     major
    -0.44
    major
    -0.43
    Major
    -0.42
     ​​
    -0.39
     primary
    -0.38
     Primary
    -0.38
     Lage
    -0.37
     dig
    -0.37
     partial
    -0.37
    POSITIVE LOGITS
    новниш
    0.66
     Paglinawan
    0.63
     zijne
    0.62
    Autoritní
    0.61
     zaś
    0.59
    addPreferredGap
    0.59
     surla
    0.58
    Дереккөздер
    0.58
     femininas
    0.57
     للاسماء
    0.57
    Activations Density 0.426%

    No Known Activations