© 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. 81104
    Prev
    Next
    INDEX
    Explanations

    elements and characteristics of physical objects and their interactions

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

    numbers and quantities

    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
     Internet
    -0.40
    《
    -0.39
    Tracce
    -0.38
     Boulder
    -0.37
     насељу
    -0.35
     internet
    -0.34
     mental
    -0.33
    scrollY
    -0.33
    würdig
    -0.33
    crollView
    -0.33
    POSITIVE LOGITS
    webElementXpaths
    0.78
    +#+#
    0.75
     AssemblyCulture
    0.71
     незавершена
    0.62
    IntoConstraints
    0.62
    XmlAccessorType
    0.60
     Infór
    0.60
    原始内容存档
    0.57
     Geſch
    0.56
    expandindo
    0.56
    Activations Density 0.084%

    No Known Activations