© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4421
    Prev
    Next
    INDEX
    Explanations

    terms related to church architecture and history

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

    Catholic churches or saints

    np_acts-logits-general · gemini-2.0-flash

    church and saint names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.81
     مرئيه
    -0.77
    NameInMap
    -0.70
    +:+
    -0.66
    évaluateur
    -0.66
    Alike
    -0.66
    rungsseite
    -0.65
     חיצוניים
    -0.65
     Beards
    -0.63
     Chwiliwch
    -0.62
    POSITIVE LOGITS
     Our
    0.61
     Saint
    0.60
     Virgin
    0.59
    Nuestra
    0.57
    Saint
    0.55
     Nossa
    0.54
     Virgen
    0.51
     St
    0.50
     Holy
    0.50
     Lady
    0.49
    Activations Density 0.094%

    No Known Activations