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. 10106
    Prev
    Next
    INDEX
    Explanations

    elements or keywords related to confirmation and user account management processes

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

    Foreign language fragments

    np_acts-logits-general · gemini-2.0-flash

    account verification

    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
    Rüyada
    -0.53
     parlano
    -0.50
     **/
    
    -0.43
     cae
    -0.43
     BoxDecoration
    -0.42
    itzar
    -0.41
     Superior
    -0.41
    باط
    -0.40
    ்க்க
    -0.40
     resultan
    -0.40
    POSITIVE LOGITS
    protoimpl
    0.79
    Gambas
    0.72
    twimg
    0.69
    MergeFrom
    0.68
     ویکی‌پدیا
    0.68
    ferrer
    0.62
    sizeCache
    0.62
    Hozzáférés
    0.62
     дописавши
    0.62
    RegressionTest
    0.61
    Activations Density 0.054%

    No Known Activations