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. 2457
    Prev
    Next
    INDEX
    Explanations

    terms related to continuous or constant processes and measurements

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

    Continuous and constant processes

    np_acts-logits-general · gemini-2.0-flash

    continuous deployment, infusion, variables

    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
    moiselle
    -0.82
    irited
    -0.69
     ProtoMessage
    -0.68
    awtextra
    -0.66
    Skocz
    -0.66
    CppMethod
    -0.65
    [](
    -0.65
     AssemblyCompany
    -0.64
    ArgsConstructor
    -0.63
    __(/*!
    -0.63
    POSITIVE LOGITS
     throughout
    0.73
     improvement
    0.67
    不断的
    0.63
    throughout
    0.63
    ährend
    0.62
     Improvement
    0.56
     Verbesserung
    0.54
    drip
    0.52
     effort
    0.51
     исто
    0.50
    Activations Density 0.177%

    No Known Activations