© 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. 20-GEMMASCOPE-RES-131K
    11. 58444
    Prev
    Next
    INDEX
    Explanations

    occurrences of the asterisk character used for annotations or comments in code

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

    programming documentation context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.93
    fromnode
    -0.87
    transQ
    -0.85
     AspNetCore
    -0.77
     betweenstory
    -0.75
    principalTable
    -0.75
    tvguidetime
    -0.74
    iffance
    -0.73
     sánchez
    -0.72
     indígen
    -0.72
    POSITIVE LOGITS
    *
    0.86
     *
    0.77
    ///
    0.71
     the
    0.70
    //
    0.62
    /*
    0.59
    #
    0.59
    The
    0.54
    //*
    0.53
     
    0.52
    Activations Density 0.004%

    No Known Activations