© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 18190
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "exports" in code contexts

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

    javascript exports and statistics

    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
     either
    -0.38
     intim
    -0.37
    ⎛
    -0.34
    +-+-
    -0.34
     kun
    -0.34
    Reference
    -0.34
     либо
    -0.34
    AMBI
    -0.33
     Bez
    -0.33
    繁
    -0.33
    POSITIVE LOGITS
    exports
    3.02
     exports
    1.38
    Exports
    1.25
     Exports
    1.23
     exportaciones
    1.09
     exportación
    0.87
     exporta
    0.81
     propOrder
    0.80
     exporters
    0.79
     exportation
    0.78
    Activations Density 0.000%

    No Known Activations