Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 12762
    Prev
    Next
    INDEX
    Explanations

    names or terms associated with mythology and deities

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

    starting with capital letters 'A' through 'G' or 'W', followed by two more letters

    np_acts-logits-general · gemini-2.0-flash

    Dy-, Wy-, Gy-, Ay- names or terms

    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
    s
    -0.96
    n
    -0.78
    a
    -0.74
    ski
    -0.73
    som
    -0.72
    sle
    -0.70
    e
    -0.67
    san
    -0.67
    sf
    -0.66
    ska
    -0.66
    POSITIVE LOGITS
    таратура
    0.61
    tagHelperRunner
    0.51
    Dislikes
    0.50
    ey
    0.48
     AssemblyProduct
    0.48
    CultureInfo
    0.45
    moveToNext
    0.44
    giène
    0.43
    tl
    0.43
     مشين
    0.42
    Activations Density 0.205%

    No Known Activations