© 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. 58339
    Prev
    Next
    INDEX
    Explanations

    UI component identifiers in a programming context

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

    UI code and conversation turns

    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
     CreateTagHelper
    -1.07
     Chwiliwch
    -0.92
    tagHelperRunner
    -0.87
    AndEndTag
    -0.84
    niſſe
    -0.81
    rungsseite
    -0.79
     InputDecoration
    -0.79
    RenderAtEndOf
    -0.78
    AutoScaleMode
    -0.77
     BoxFit
    -0.77
    POSITIVE LOGITS
    //
    0.35
    K
    0.34
    .
    0.33
    0.32
    P
    0.32
     кле
    0.31
    TM
    0.31
    ള
    0.31
    layout
    0.31
    PC
    0.31
    Activations Density 0.004%
    No Known Activations