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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 24244
    Prev
    Next
    INDEX
    Explanations

    key indicators and expressions related to time and temporal reference

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

    date, time, or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    
    -0.71
    TagMode
    -0.70
     وتسجيلات
    -0.67
     AssemblyCompany
    -0.65
     الرياضيه
    -0.62
     HasFactory
    -0.62
    AccessFile
    -0.62
     betweenstory
    -0.61
     تضيفلها
    -0.61
    
    -0.60
    POSITIVE LOGITS
     eenvou
    0.26
     माल
    0.24
     kimse
    0.23
    ///</
    0.23
     الآ
    0.23
    ⓧ
    0.23
    Do
    0.22
     önem
    0.21
    Simple
    0.21
     bowiem
    0.21
    Activations Density 0.017%

    No Known Activations