© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13909
    Prev
    Next
    INDEX
    Explanations

    references to God and divine concepts along with the themes of faith and spirituality

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

    God

    np_acts-logits-general · gemini-2.0-flash

    God, father, Lamb

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    oa̍t
    -0.54
    FontOfSize
    -0.53
    PreferredItem
    -0.49
     overlap
    -0.45
    onResume
    -0.44
    发表于
    -0.43
     pinulongan
    -0.43
     ویکی‌پدی
    -0.42
    ership
    -0.41
     Overnight
    -0.41
    POSITIVE LOGITS
     God
    0.76
    God
    0.72
     GOD
    0.63
     Dumnezeu
    0.58
     Almighty
    0.57
    GOD
    0.56
     god
    0.53
    god
    0.50
     Tuhan
    0.50
     Dieu
    0.50
    Activations Density 0.133%

    No Known Activations