© 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. 1882
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and their officials

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

    universities and their associated institutions

    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
    uminescence
    -0.51
     industrie
    -0.46
     Sentinel
    -0.46
    ieważ
    -0.45
    inella
    -0.45
    InitVars
    -0.44
    syscall
    -0.43
    lick
    -0.43
     oportun
    -0.43
     mercen
    -0.43
    POSITIVE LOGITS
     Oxford
    0.99
     oxford
    0.88
    Oxford
    0.87
     Cambridge
    0.87
    parsedMessage
    0.82
    Cambridge
    0.81
     OXFORD
    0.81
     виправивши
    0.78
     Radcliffe
    0.78
     Cowley
    0.76
    Activations Density 0.139%

    No Known Activations