© 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. 15-GEMMASCOPE-RES-16K
    11. 2086
    Prev
    Next
    INDEX
    Explanations

    references to holiness and sacredness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.81
    OGND
    -0.75
    IsContent
    -0.75
     Himo
    -0.73
     Orpheus
    -0.71
    awtextra
    -0.70
     مرئيه
    -0.70
     للاسماء
    -0.68
     NSCoder
    -0.68
     estekak
    -0.67
    POSITIVE LOGITS
     Holy
    0.84
     holy
    0.79
     bless
    0.77
    Holy
    0.72
     blessed
    0.64
     HOLY
    0.64
    blessed
    0.63
    HOLY
    0.62
     Bless
    0.61
    Bless
    0.60
    Activations Density 0.099%

    No Known Activations