© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 6506
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "documentary" and newline characters in the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     doInBackground
    -0.75
    ')):
    -0.71
    ThroughAttribute
    -0.69
    __':
    -0.67
    >*/
    -0.66
    Brainz
    -0.66
    __":
    -0.65
    __":
    -0.65
    ()?;
    -0.64
    __':
    -0.63
    POSITIVE LOGITS
    CodeDom
    0.59
    getDrawable
    0.58
    ون
    0.56
     exoner
    0.56
     跳转至
    0.56
     SDL
    0.55
    чим
    0.54
    tq
    0.53
    ondag
    0.53
    adal
    0.52
    Activations Density 0.054%

    No Known Activations