© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1303
    Prev
    Next
    INDEX
    Explanations

    structured URL elements and query parameters related to searches and content on web pages

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

    URLs and references to online resources

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

    search, Scotland, boolean

    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
    migrationBuilder
    -0.78
     Houſe
    -0.78
    +#+#
    -0.77
    تقاوى
    -0.73
     Reſ
    -0.69
    Ārējās
    -0.69
     Monfieur
    -0.67
     Majefty
    -0.66
     Perſ
    -0.66
     Theſe
    -0.65
    POSITIVE LOGITS
     '\\;'
    0.58
    setVerticalGroup
    0.52
    ⓘ
    0.46
    ROME
    0.42
    hl
    0.42
     search
    0.42
    hler
    0.42
    واه
    0.41
    꼴
    0.41
    Pa
    0.41
    Activations Density 0.033%

    No Known Activations