© 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. 31-GEMMASCOPE-RES-16K
    11. 2919
    Prev
    Next
    INDEX
    Explanations

    code-related terms and error handling mechanisms in programming contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    API client method implementations and REST API calls in Go code.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Rea
    -0.32
     cá
    -0.30
     bond
    -0.29
     sau
    -0.28
    代
    -0.28
     
    -0.27
     activation
    -0.26
     Hend
    -0.26
     dan
    -0.25
     SCO
    -0.25
    POSITIVE LOGITS
     autorytatywna
    0.80
    transQ
    0.75
     nahilalakip
    0.72
    OGND
    0.70
    ſicht
    0.67
    windowFixed
    0.67
     nakalista
    0.66
    ſehen
    0.65
    原始内容存档于
    0.64
    httphttps
    0.64
    Activations Density 0.593%

    No Known Activations