© 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. 20-GEMMASCOPE-RES-131K
    11. 32891
    Prev
    Next
    INDEX
    Explanations

    function and method calls related to output and logging in programming code

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

    writing or printing code

    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
    
    -0.83
    RenderAtEndOf
    -0.78
    
    -0.75
    RotationOrder
    -0.71
    tagHelperRunner
    -0.71
     للمعارف
    -0.70
    TagMode
    -0.69
    MLLoader
    -0.68
     ब्रेकडाउन
    -0.68
     kasarigan
    -0.68
    POSITIVE LOGITS
    print
    0.50
    Printf
    0.44
    printf
    0.43
    Println
    0.40
    println
    0.38
    cout
    0.36
     print
    0.36
    fprintf
    0.34
    ylabel
    0.34
    write
    0.32
    Activations Density 0.002%

    No Known Activations