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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11965
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and control flow elements, particularly in the context of error handling and exit procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreExecute
    -0.35
     mulus
    -0.32
     actionPerformed
    -0.32
     meman
    -0.30
    umerate
    -0.29
     compter
    -0.29
    繰り
    -0.28
     cár
    -0.28
     ivelany
    -0.28
     obchod
    -0.28
    POSITIVE LOGITS
     exit
    1.62
    exit
    1.54
     Exit
    1.45
    Exit
    1.36
     exits
    1.33
     EXIT
    1.25
     exiting
    1.19
    EXIT
    1.17
    quit
    1.11
    Quit
    1.11
    Activations Density 0.297%

    No Known Activations