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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 5347
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions related to linear mappings and density operators

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

    Preceding words like "any", "all", "some," or "a"

    np_acts-logits-general · gemini-2.0-flash

    articles and specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     piña
    -0.55
    Przypisy
    -0.54
    ']=='
    -0.53
    ']==
    -0.48
     anvil
    -0.48
     curie
    -0.47
    anyaan
    -0.47
     flamb
    -0.46
     sleepers
    -0.45
    <>
    -0.45
    POSITIVE LOGITS
    LookAnd
    0.80
    Hentet
    0.76
    IsMutable
    0.71
    RenderAtEndOf
    0.71
     سكانية
    0.70
    onViewCreated
    0.68
    Filmografia
    0.65
    addContainerGap
    0.65
    Бахар
    0.63
     nonnegative
    0.61
    Activations Density 1.768%

    No Known Activations