© 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. 66720
    Prev
    Next
    INDEX
    Explanations

    the presence of indentation or whitespace characters in text

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

    code comments and structure

    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
    rboles
    -0.50
     Câmara
    -0.41
    []>(
    -0.36
     vila
    -0.36
    [];
    -0.35
    ꜱ
    -0.35
     polícia
    -0.34
     trail
    -0.33
     bandeira
    -0.33
     dags
    -0.33
    POSITIVE LOGITS
     intptr
    0.83
    HasAnnotation
    0.71
     &___
    0.64
    HXLINE
    0.63
    Tembelea
    0.62
     TextAlign
    0.62
    uxxxx
    0.61
    setViewportView
    0.60
     '{@
    0.57
    WireFormatLite
    0.56
    Activations Density 0.049%

    No Known Activations