© 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. 24-GEMMASCOPE-RES-16K
    11. 1977
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "dark" in various contexts

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

    "dark" or its variations

    np_acts-logits-general · gemini-2.0-flash

    dark + matter or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cotch
    -0.70
     mismos
    -0.65
     NSCoder
    -0.65
     ujednoznacz
    -0.64
    PerPage
    -0.63
     Roskov
    -0.63
     MainAxisSize
    -0.59
    ANEOUS
    -0.59
    CodeAttribute
    -0.59
    aneous
    -0.58
    POSITIVE LOGITS
     dark
    1.11
     Dark
    1.01
    Dark
    0.97
    dark
    0.95
     DARK
    0.95
    DARK
    0.92
     oscuro
    0.86
     gelap
    0.69
     Ages
    0.67
     escuro
    0.67
    Activations Density 0.056%

    No Known Activations