© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13379
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "holy" or "holiness"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.75
    sizeCache
    -0.65
    iastes
    -0.64
    رشف
    -0.61
     disambiguazione
    -0.59
     препратки
    -0.59
     مشين
    -0.59
    posedge
    -0.59
    queryInterface
    -0.58
     <=",
    -0.57
    POSITIVE LOGITS
     Holy
    1.80
     holy
    1.77
    Holy
    1.64
     HOLY
    1.54
    holy
    1.46
    HOLY
    1.33
     sacred
    0.87
     heilige
    0.85
     Sacred
    0.83
     Heilige
    0.79
    Activations Density 0.104%

    No Known Activations