© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1844
    Prev
    Next
    INDEX
    Explanations

    references to specific geopolitical contexts or regions

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

    Mudari, Makkan

    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
    SourceChecksum
    -0.93
    queryInterface
    -0.75
    findpost
    -0.68
    bewerken
    -0.59
    verwijspagina
    -0.56
    ⓧ
    -0.55
     demais
    -0.55
     Exacts
    -0.53
    expandindo
    -0.52
    коменду
    -0.52
    POSITIVE LOGITS
     pinulongan
    0.60
    adda
    0.50
    endsection
    0.50
    askins
    0.46
    INCT
    0.46
     оригіналу
    0.45
    gister
    0.45
    uinal
    0.45
    enumii
    0.44
    AMED
    0.44
    Activations Density 0.026%

    No Known Activations