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. 16-GEMMASCOPE-RES-16K
    6. 1567
    Prev
    Next
    INDEX
    Explanations

    quantitative results represented in a structured manner

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

    Mathematical/scientific notation: Greek letters

    np_acts-logits-general · gemini-2.0-flash

    (a), (b), (c) labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     A
    -0.60
    🅰
    -0.56
    a
    -0.55
    帖最后由
    -0.54
    ắ
    -0.53
    setof
    -0.52
    SpringBootTest
    -0.51
    DeleteBehavior
    -0.51
     a
    -0.50
     Ohl
    -0.48
    POSITIVE LOGITS
    issau
    0.60
     محفوظة
    0.60
    !*\
    0.58
     lenker
    0.58
    xically
    0.58
     Paglinawan
    0.58
    مصادر
    0.55
    ześnie
    0.54
     Wikispecies
    0.53
     picioare
    0.53
    Activations Density 0.271%

    No Known Activations