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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7895
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "export" in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.55
     propOrder
    -0.46
     resourceCulture
    -0.46
    MeasureSpec
    -0.44
    MergeFrom
    -0.44
     ContentValues
    -0.43
    原始内容存档于
    -0.43
     kautta
    -0.41
     للاسماء
    -0.41
     JAXB
    -0.41
    POSITIVE LOGITS
     default
    0.54
     function
    0.52
     const
    0.49
     let
    0.48
     async
    0.46
     اکس
    0.43
     var
    0.43
    {};
    0.42
     class
    0.40
     interface
    0.40
    Activations Density 0.065%

    No Known Activations