© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5873
    Prev
    Next
    INDEX
    Explanations

    references to religious figures or church-related terminology

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

    details about religious roles, church leadership, and Anglican church positions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    lovakia
    -0.45
     implied
    -0.40
    filter
    -0.39
     filtered
    -0.39
     MISSING
    -0.38
    Filter
    -0.38
    Filtered
    -0.36
     Pemer
    -0.36
     EXPER
    -0.36
     skr
    -0.36
    POSITIVE LOGITS
     churches
    0.71
    Архівовано
    0.68
     church
    0.67
     Church
    0.63
    httphttps
    0.62
     pastor
    0.60
    church
    0.60
    MLLoader
    0.60
     pastors
    0.59
     congregations
    0.58
    Activations Density 0.121%

    No Known Activations