© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27548
    Prev
    Next
    INDEX
    Explanations

    the mention of dates, specifically in the month of December

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

    court citations and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.72
     stanovnika
    -0.65
    AlterField
    -0.64
     Shakspeare
    -0.63
    EndGlobalSection
    -0.63
    WebElementEntity
    -0.63
     createSprite
    -0.62
     dortmund
    -0.61
    elemField
    -0.60
     Ruman
    -0.60
    POSITIVE LOGITS
    日閲覧
    3.53
    脚注
    1.07
     مشين
    0.95
    UpInside
    0.94
     FetchType
    0.90
    脚注の使い方
    0.86
     सत्यापित
    0.72
     consultato
    0.66
    Tembelea
    0.64
    存于互联网档案馆
    0.64
    Activations Density 0.001%

    No Known Activations