© 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. 1-GEMMASCOPE-RES-16K
    11. 11754
    Prev
    Next
    INDEX
    Explanations

    structures and definitions within programming code

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     queſta
    -1.80
     ſind
    -1.73
    <unused41>
    -1.70
    <unused14>
    -1.70
    <unused74>
    -1.70
    <unused43>
    -1.70
    <unused8>
    -1.70
    <unused23>
    -1.69
    <unused3>
    -1.69
    [@BOS@]
    -1.69
    POSITIVE LOGITS
    ↵
    1.75
    ↵↵
    1.25
    .
    1.10
    ↵↵↵
    1.10
    </tr>
    0.95
    ↵↵↵↵
    0.94
    ,
    0.87
    <bos>
    0.86
    (
    0.83
    ↵↵↵↵↵
    0.80
    Activations Density 1.899%

    No Known Activations