© 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 EvalsExportsAPI 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. 83940
    Prev
    Next
    INDEX
    Explanations

    occurrences of the asterisk character used in documentation or code comments

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

    method names

    np_acts-logits-general · gemini-2.5-flash-lite

    Lines that begin with or contain the '*' used as a block-comment/Javadoc leading asterisk.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    
    -0.95
    principalTable
    -0.78
    Jereo
    -0.75
     IBOutlet
    -0.75
     queſta
    -0.73
    oneofs
    -0.72
    sizeCache
    -0.70
    parsedMessage
    -0.70
    PerformLayout
    -0.69
    principalColumn
    -0.68
    POSITIVE LOGITS
     *
    0.73
    *
    0.59
    //
    0.59
     the
    0.54
    ///
    0.52
     a
    0.49
     //
    0.48
     
    0.46
    #
    0.43
    The
    0.42
    Activations Density 0.003%

    No Known Activations