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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 10369
    Prev
    Next
    INDEX
    Explanations

    technical terms and equations related to physics and particle interactions.

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

    mathematical equations or formulae related to physics.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    scientific and mathematical terminology, particularly related to particle physics and quantum field theory.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Follows prepositions, especially "of" and "the"

    np_acts-logits-general · gemini-2.0-flash

    QCD perturbation series and Borel summation

    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
     Syndicate
    -0.57
     baud
    -0.56
    genstein
    -0.53
    تقاوى
    -0.52
     Thess
    -0.49
    シューズ
    -0.49
    posedge
    -0.48
    rigado
    -0.47
    BeforeClass
    -0.47
    릎
    -0.47
    POSITIVE LOGITS
    CMY
    0.52
    QCD
    0.52
    Adel
    0.51
     Adel
    0.50
    ()],
    0.48
    vinger
    0.47
     SRC
    0.46
     jel
    0.45
    ัติ
    0.45
    getOut
    0.45
    Activations Density 0.601%

    No Known Activations