© 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. 13-GEMMASCOPE-RES-65K
    11. 8011
    Prev
    Next
    INDEX
    Explanations

    the presence and variations of the word "undertake" and its forms 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 @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    fxml
    -0.76
    djangoproject
    -0.75
     Mosley
    -0.74
     Greer
    -0.72
     Felix
    -0.70
     Callahan
    -0.67
     Apu
    -0.65
     bells
    -0.64
     Barnes
    -0.64
     Xi
    -0.64
    POSITIVE LOGITS
     undertaken
    1.62
     undertake
    1.60
     undertook
    1.50
     undertakes
    1.49
     undertaking
    1.29
     undertakings
    1.20
    takings
    0.96
    taking
    0.95
     ویکی‌پدی
    0.91
    takes
    0.89
    Activations Density 0.011%

    No Known Activations