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. 9403
    Prev
    Next
    INDEX
    Explanations

    references to biblical scriptures and teachings

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

    books of the Bible

    np_acts-logits-general · gemini-2.0-flash

    bible book citations

    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
    farwyddwr
    -0.58
    tvguidetime
    -0.55
     oslo
    -0.53
    PRNewswire
    -0.52
    ="@+
    -0.51
    SharedDtor
    -0.49
    PMailer
    -0.47
    WithIdentifier
    -0.47
    IntoConstraints
    -0.47
    CDATA
    -0.46
    POSITIVE LOGITS
     Matthew
    0.96
     Luke
    0.91
    Matthew
    0.82
     Genesis
    0.80
    Luke
    0.80
     Ephesians
    0.78
     Romans
    0.77
     Psalm
    0.76
     Mathew
    0.73
     Matt
    0.72
    Activations Density 0.125%

    No Known Activations