© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15313
    Prev
    Next
    INDEX
    Explanations

    references to religious figures and elements associated with tradition and history

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

    religious figures/concepts

    np_acts-logits-general · gemini-2.0-flash

    Jesus, Christ, Santa, God

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    aarrggbb
    -0.67
    OGND
    -0.54
     initComponents
    -0.52
    getMenuInflater
    -0.52
    nesc
    -0.50
    Hochspringen
    -0.49
    TestingModule
    -0.48
    gdx
    -0.48
    RefreshLayout
    -0.48
    Comté
    -0.44
    POSITIVE LOGITS
     Jesus
    1.12
     Santa
    0.96
     Saint
    0.93
    Jesus
    0.91
     Christ
    0.90
    Santa
    0.81
     saint
    0.79
    Saint
    0.79
     JESUS
    0.78
     Satan
    0.78
    Activations Density 0.286%

    No Known Activations