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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7721
    Prev
    Next
    INDEX
    Explanations

    references to the divine or spiritual authority

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

    baptism, Spirit, or tongues

    np_acts-logits-general · gemini-2.0-flash

    gifts of the Spirit

    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
    SpringBootTest
    -0.56
     defaultstate
    -0.56
    gero
    -0.51
    rigo
    -0.50
    ayer
    -0.49
    Гео
    -0.49
     cjs
    -0.48
    erval
    -0.48
    alte
    -0.48
    logio
    -0.47
    POSITIVE LOGITS
     Spirit
    0.85
    Spirit
    0.73
     Espíritu
    0.73
     spirit
    0.70
    Esprit
    0.69
     Holy
    0.66
     Spirito
    0.64
    spirit
    0.63
     Spirits
    0.61
     SPIRIT
    0.60
    Activations Density 0.072%

    No Known Activations