© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 270
    Prev
    Next
    INDEX
    Explanations

    coding syntax elements, specifically those related to control structures and loops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     return
    -0.96
     returning
    -0.82
    return
    -0.79
     Rückkehr
    -0.79
     returned
    -0.74
     RETURN
    -0.73
     Return
    -0.73
     Returning
    -0.70
     returns
    -0.69
     возвра
    -0.66
    POSITIVE LOGITS
    continue
    0.45
    continued
    0.39
     endforeach
    0.38
    endfor
    0.38
     Continued
    0.38
     חיצוניים
    0.37
     continue
    0.36
    if
    0.36
    Continued
    0.36
     contributions
    0.36
    Activations Density 0.210%

    No Known Activations