© 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. 23-GEMMASCOPE-RES-16K
    11. 6428
    Prev
    Next
    INDEX
    Explanations

    control flow statements and their associated keywords in 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 @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    IndentedString
    -0.55
    kezett
    -0.54
     يتيمه
    -0.53
    IntoConstraints
    -0.49
     verſch
    -0.48
    resented
    -0.48
    Fails
    -0.48
     igjen
    -0.47
    resentation
    -0.47
    Demografía
    -0.47
    POSITIVE LOGITS
     stop
    0.71
     stops
    0.61
     STOP
    0.60
     Stop
    0.58
    stop
    0.58
     stopped
    0.57
     stopping
    0.55
    STOP
    0.54
    Stop
    0.52
     prematurely
    0.50
    Activations Density 0.312%

    No Known Activations