Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15735
    Prev
    Next
    INDEX
    Explanations

    references to religious institutions and their historical context

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

    churches and religion

    np_acts-logits-general · gemini-2.0-flash

    locations of churches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nawr
    -0.54
     nahilalakip
    -0.52
     tokens
    -0.51
    zard
    -0.51
     lactation
    -0.51
    westen
    -0.50
     Geschäftsführer
    -0.50
    مصادر
    -0.50
    apnews
    -0.49
     calldata
    -0.49
    POSITIVE LOGITS
     church
    0.79
     Church
    0.74
    église
    0.73
     Iglesia
    0.72
     église
    0.71
     iglesia
    0.71
     churches
    0.70
     CHURCH
    0.68
     Église
    0.64
     chiesa
    0.64
    Activations Density 0.106%

    No Known Activations