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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4235
    Prev
    Next
    INDEX
    Explanations

    terms related to the mathematical modeling of diffusion processes in physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     propOrder
    -0.51
    Membership
    -0.48
    lader
    -0.46
     prega
    -0.45
     lief
    -0.45
    design
    -0.45
     scio
    -0.44
    abases
    -0.44
    asian
    -0.44
     Membership
    -0.43
    POSITIVE LOGITS
    ReusableCell
    0.70
    لينكات
    0.64
     typelib
    0.63
    webElementXpaths
    0.63
    :✨
    0.59
     Normdatei
    0.59
    parsedMessage
    0.59
    Datuak
    0.58
     autocorrelation
    0.57
    rrggbb
    0.56
    Activations Density 1.661%

    No Known Activations