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. 9383
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific concepts and experimental methodologies

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

    Mathematical or physics equations/symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and energy

    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
    rungsseite
    -0.78
     []:
    -0.55
     Baillargeon
    -0.54
     hjel
    -0.53
     schä
    -0.53
    rrggbb
    -0.52
     '\\;'
    -0.51
    OGND
    -0.51
     ویکی‌پدیا
    -0.50
    grund
    -0.49
    POSITIVE LOGITS
     energies
    0.66
    GetKeyDown
    0.59
     Energies
    0.57
     energy
    0.54
     glucos
    0.53
    energies
    0.53
     الحره
    0.52
     Ener
    0.51
    energy
    0.51
    omenta
    0.50
    Activations Density 1.068%

    No Known Activations