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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8471
    Prev
    Next
    INDEX
    Explanations

    terms related to Catholic religious life and community

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

    Religious orders and societies

    np_acts-logits-general · gemini-2.0-flash

    Religious orders and clergy

    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
     considérons
    -0.52
     linkovi
    -0.49
    Lähteet
    -0.46
     megt
    -0.45
    präsident
    -0.45
    inander
    -0.44
    doğan
    -0.44
    ərbaycan
    -0.43
    Autoritní
    -0.42
     starboard
    -0.42
    POSITIVE LOGITS
     monks
    1.08
     nuns
    1.04
     monastic
    1.02
     monk
    1.00
     nun
    0.99
     Order
    0.98
     convent
    0.95
     Sisters
    0.94
     Monks
    0.91
     Sister
    0.91
    Activations Density 0.161%

    No Known Activations