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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6825
    Prev
    Next
    INDEX
    Explanations

    references to permissions and constraints related to software usage

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

    Code, paths, and programming structures

    np_acts-logits-general · gemini-2.0-flash

    code structure and data types

    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
     surla
    -0.61
    AntiForgeryToken
    -0.56
    ViewImports
    -0.51
    GRANTED
    -0.50
    uldu
    -0.48
    mıştır
    -0.48
    //
    -0.48
     tap
    -0.47
    tap
    -0.47
    MENAFN
    -0.46
    POSITIVE LOGITS
     propOrder
    0.83
    IndentedString
    0.69
    GEBURTSDATUM
    0.65
     الاطلاع
    0.57
    colgroup
    0.57
     betweenstory
    0.57
    Portály
    0.56
     cherchés
    0.53
    tikzpicture
    0.52
    :✨
    0.51
    Activations Density 0.031%

    No Known Activations