© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14740
    Prev
    Next
    INDEX
    Explanations

    events related to political rallies and public gatherings

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

    Events, rallies, and public appearances

    np_acts-logits-general · gemini-2.0-flash

    events and gatherings

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    testens
    -0.52
     vectorielles
    -0.51
     ourselves
    -0.49
    cutta
    -0.48
     pendientes
    -0.48
    Хотя
    -0.47
    apiVersion
    -0.45
     pendiente
    -0.44
    ojo
    -0.43
     хотя
    -0.43
    POSITIVE LOGITS
     Taktlose
    0.73
    TagMode
    0.71
     programme
    0.69
    ंदीखरीदारी
    0.68
    UnusedPrivate
    0.68
    RenderAtEndOf
    0.67
    المكان
    0.66
     propOrder
    0.64
     समीक्षाओं
    0.63
     PeEnEo
    0.63
    Activations Density 0.050%

    No Known Activations