© 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. 13775
    Prev
    Next
    INDEX
    Explanations

    occurrences of empty object notation in code or data structures

    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
    an
    -0.93
    le
    -0.85
    in
    -0.83
    ن
    -0.79
    -
    -0.78
    de
    -0.77
    way
    -0.76
    us
    -0.75
    WriteLiteral
    -0.73
    es
    -0.73
    POSITIVE LOGITS
     للمعارف
    1.09
     ainfi
    1.06
     {}
    1.05
    ("{}
    1.05
     auffi
    1.02
     theſe
    0.99
     purpoſe
    0.99
     feroit
    0.98
    !("{}",
    0.98
    :{}
    0.95
    Activations Density 0.042%

    No Known Activations