© 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. 56
    Prev
    Next
    INDEX
    Explanations

    references to church-related events and structures

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

    references to religious events, specifically Christmas Eve and church services

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

    church and religious buildings

    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
     nahilalakip
    -0.52
    Executives
    -0.52
     Wires
    -0.51
    ÓD
    -0.51
    ddots
    -0.50
     Италијани
    -0.49
     game
    -0.48
    ésultat
    -0.47
    }))
    -0.46
    bitat
    -0.45
    POSITIVE LOGITS
     church
    1.12
     churches
    1.06
     Church
    0.99
     CHURCH
    0.91
    Church
    0.90
     Église
    0.89
    church
    0.88
    église
    0.88
     église
    0.86
     Iglesia
    0.84
    Activations Density 0.143%

    No Known Activations