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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16080
    Prev
    Next
    INDEX
    Explanations

    references to worship and church leadership roles

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

    references to Christian faith, church activities, and religious community.

    oai_token-act-pair · gpt-4.1-2025-04-14Triggered by @ywhp2c8tjm

    words relating to Christianity and spiritual practice.

    oai_token-act-pair · gemini-2.0-flashTriggered by @ywhp2c8tjm
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     Vorder
    -0.38
    ENODEV
    -0.36
     Arora
    -0.36
     Exchequer
    -0.35
    passen
    -0.35
     населення
    -0.33
     lucky
    -0.33
     gegenüber
    -0.33
     Pliny
    -0.33
    ierend
    -0.32
    POSITIVE LOGITS
    aarrggbb
    0.72
    webElementGuid
    0.68
     pastors
    0.68
    adaptiveStyles
    0.64
     nahilalakip
    0.64
    cuadro
    0.61
     Bible
    0.57
     pastor
    0.56
    ionales
    0.54
     esboço
    0.51
    Activations Density 0.272%

    No Known Activations