© 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. 67405
    Prev
    Next
    INDEX
    Explanations

    commands related to plotting and graphing data visualizations in programming

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

    plotting and graphing 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
     ब्रेकडाउन
    -0.79
    WriteTagHelper
    -0.73
    RTEE
    -0.71
    AndEndTag
    -0.62
    parsedMessage
    -0.60
    FunctionFlags
    -0.59
    Tembelea
    -0.57
    thâu
    -0.56
    verifyException
    -0.54
    httphttps
    -0.51
    POSITIVE LOGITS
    pyplot
    0.67
     pyplot
    0.52
     visuals
    0.47
     presentation
    0.44
     graphs
    0.44
     presentations
    0.43
     pictorial
    0.43
     pictures
    0.42
     graphics
    0.42
     visualizations
    0.41
    Activations Density 0.020%

    No Known Activations