© 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. 109830
    Prev
    Next
    INDEX
    Explanations

    blank spaces or empty elements in a structured format

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

    html closing tags

    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
     समीक्षाओं
    -0.87
    OGND
    -0.86
    ChildScrollView
    -0.78
     незавершена
    -0.77
     nahilalakip
    -0.73
    :✨
    -0.73
     queſta
    -0.73
     NSCoder
    -0.71
    fjspx
    -0.71
     defStyleAttr
    -0.70
    POSITIVE LOGITS
     
    0.36
    Doppel
    0.34
    No
    0.33
     synthetic
    0.33
    ULATOR
    0.32
    <strong>
    0.32
    IONI
    0.32
     [
    0.31
    alt
    0.31
     stuffed
    0.31
    Activations Density 0.005%

    No Known Activations