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. 10148
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to programming and computing

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

    Follows "Q:" or contains code snippets

    np_acts-logits-general · gemini-2.0-flash

    questions and updates

    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
    󠁿
    -1.07
    }{*}{}
    -0.78
    WithFormat
    -0.74
     المعيارى
    -0.72
    μβρίου
    -0.67
    ')['
    -0.59
    UVWXYZ
    -0.59
    üyada
    -0.58
    ьажоргаш
    -0.58
    intios
    -0.56
    POSITIVE LOGITS
     Majefty
    0.81
    Geplaatst
    0.80
     EnglishChoose
    0.77
     Вікіпе
    0.77
    ﹍﹍﹍
    0.77
     تعدى
    0.76
     fhew
    0.74
     AssemblyCompany
    0.74
     Anfitrión
    0.71
     AssemblyCulture
    0.70
    Activations Density 4.254%

    No Known Activations