© 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. 6558
    Prev
    Next
    INDEX
    Explanations

    references to screws and the concept of being lean

    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
     świad
    -0.52
     wezen
    -0.51
    chod
    -0.51
    licó
    -0.50
     Prior
    -0.50
    plet
    -0.50
    dawg
    -0.49
    Prior
    -0.49
     Tatsache
    -0.48
    Personensuche
    -0.47
    POSITIVE LOGITS
     screws
    0.96
     Screws
    0.83
    scre
    0.81
     screwed
    0.77
    Accessors
    0.75
     SUV
    0.73
     Scre
    0.70
     lean
    0.70
     jsPsych
    0.69
    inerja
    0.68
    Activations Density 0.076%

    No Known Activations