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. 3182
    Prev
    Next
    INDEX
    Explanations

    financial contributions to education-related initiatives

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

    following "to" or related to funding

    np_acts-logits-general · gemini-2.0-flash

    money for projects and expenses

    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
     استنادى
    -0.54
     bounding
    -0.51
    LayoutStyle
    -0.51
    TintMode
    -0.49
    adpleegd
    -0.48
    았
    -0.47
     Tất
    -0.46
    ंप
    -0.46
     vendre
    -0.46
     questioning
    -0.46
    POSITIVE LOGITS
     purchase
    0.81
     defray
    0.74
     renovations
    0.73
     expenses
    0.70
     fund
    0.69
     membeli
    0.69
     <<<<<<<<<<<<<<
    0.66
     projects
    0.65
    purchase
    0.64
     needy
    0.64
    Activations Density 0.240%

    No Known Activations