© 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. 3180
    Prev
    Next
    INDEX
    Explanations

    references to programming or coding language syntax elements

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

    code syntax elements and programming language structures.

    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
     karan
    -0.35
     TLR
    -0.34
     Athe
    -0.33
    EMY
    -0.32
    Collegamenti
    -0.32
     BSP
    -0.31
    BSP
    -0.31
     PSD
    -0.31
     Bag
    -0.31
     Gait
    -0.31
    POSITIVE LOGITS
     sheet
    0.90
     Sheet
    0.84
    Sheet
    0.84
     cell
    0.83
     cells
    0.82
     Zellen
    0.79
     spreadsheet
    0.78
     Cells
    0.77
     sheets
    0.76
     SHEET
    0.76
    Activations Density 0.175%

    No Known Activations