© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 82400
    Prev
    Next
    INDEX
    Explanations

    instances of the term "execute" in a programming or database context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    execute programming commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tdessen
    -0.38
    归
    -0.38
    歸
    -0.34
    Havolalar
    -0.32
     dalla
    -0.29
    middot
    -0.29
     Dend
    -0.28
    malıdır
    -0.28
    mn
    -0.28
     contrasts
    -0.28
    POSITIVE LOGITS
    execute
    2.48
     execute
    1.73
     Execute
    1.55
    Execute
    1.51
     executing
    1.30
     executes
    1.30
     executed
    1.30
     execution
    1.24
     EXEC
    1.20
    EXECUTE
    1.20
    Activations Density 0.002%

    No Known Activations