© 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. 18-GEMMASCOPE-RES-16K
    11. 1695
    Prev
    Next
    INDEX
    Explanations

    references to a higher power or divinity, particularly in a prayer or spiritual context

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

    after commas or brackets

    np_acts-logits-general · gemini-2.0-flash

    Lord, Seigneur, Signore, filed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORT
    -0.54
    Geplaatst
    -0.50
    చి
    -0.48
    IONES
    -0.47
    ΕΙ
    -0.47
    esez
    -0.47
    BeginContext
    -0.47
    astify
    -0.47
    nitive
    -0.46
    GetAsync
    -0.46
    POSITIVE LOGITS
     Lord
    0.73
    Lord
    0.72
    featureID
    0.72
    AddHtmlAttribute
    0.65
    LORD
    0.64
    ftagPool
    0.62
     Seigneur
    0.61
     getItemId
    0.59
     Signore
    0.58
     lord
    0.56
    Activations Density 0.052%

    No Known Activations