© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3107
    Prev
    Next
    INDEX
    Explanations

    specific character patterns or formatting in text

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

    special characters or code segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    IUrlHelper
    -0.77
    MethodManager
    -0.73
    ViewFeatures
    -0.66
     kaynağından
    -0.64
     estekak
    -0.62
    XmlRootElement
    -0.61
    AccessFile
    -0.60
    Artik
    -0.60
    principalTable
    -0.60
    )");
    -0.59
    POSITIVE LOGITS
    IntoConstraints
    0.76
     internetowa
    0.58
     stb
    0.54
     وتسجيلات
    0.53
    sidemargin
    0.50
     useEffect
    0.48
     通販
    0.48
    حوالہ
    0.48
     izquier
    0.47
     usw
    0.47
    Activations Density 0.324%

    No Known Activations