© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6277
    Prev
    Next
    INDEX
    Explanations

    references to churches and related structures in a religious context

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

    the word "church"

    np_acts-logits-general · gemini-2.0-flash

    church, iglesia, igreja

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catching
    -0.50
    slot
    -0.50
    量
    -0.47
    Gemini
    -0.46
    TabIndex
    -0.46
     Mojave
    -0.46
    Slot
    -0.45
    laught
    -0.45
    shl
    -0.44
     Nitro
    -0.44
    POSITIVE LOGITS
     Church
    1.97
     church
    1.85
    Church
    1.83
     CHURCH
    1.80
    church
    1.63
    CHURCH
    1.52
     iglesia
    1.43
     Churches
    1.39
     churches
    1.38
     igreja
    1.36
    Activations Density 0.071%

    No Known Activations