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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1267
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to health and environmental sustainability

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

    news or scientific studies

    np_acts-logits-general · gemini-2.0-flash

    news, climate, impact, edema, cells, affect, biomass, create, access

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Breda
    -0.34
     narzęd
    -0.34
     parç
    -0.33
     händer
    -0.32
     Uch
    -0.31
    AutoField
    -0.31
    aaral
    -0.31
     LCD
    -0.31
     Vergara
    -0.31
     par
    -0.30
    POSITIVE LOGITS
     kasarigan
    0.87
    TagMode
    0.73
    Vidite
    0.62
     EconPapers
    0.60
    httphttps
    0.60
    thâu
    0.59
    دانشنامهٔ
    0.57
    :✨
    0.57
     Wikimedijinoj
    0.57
     للاسماء
    0.56
    Activations Density 0.871%

    No Known Activations