© 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. 22-GEMMASCOPE-RES-16K
    11. 5444
    Prev
    Next
    INDEX
    Explanations

    references to divine or godly themes

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

    Appearing after the word "God"

    np_acts-logits-general · gemini-2.0-flash

    God and religious context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stroll
    -0.56
    CloseOperation
    -0.56
     OPC
    -0.54
     utafitiHapana
    -0.53
     perpetuity
    -0.52
    conversions
    -0.52
    jų
    -0.52
     becauſe
    -0.51
     holders
    -0.50
    pkey
    -0.50
    POSITIVE LOGITS
     Almighty
    0.74
     forbid
    0.72
     bless
    0.68
     GOD
    0.65
    awful
    0.63
     God
    0.61
    liness
    0.61
    damn
    0.61
    RegressionTest
    0.60
    GOD
    0.59
    Activations Density 0.051%

    No Known Activations