© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 31206
    Prev
    Next
    INDEX
    Explanations

    references to RSV (Porcine Reproductive and Respiratory Syndrome Virus) and its impact on swine health

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

    PRRSV virus causes, inhibits, reduces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     non
    -0.37
     actual
    -0.34
     intended
    -0.33
    ETHOD
    -0.33
    を行います
    -0.33
     example
    -0.32
     good
    -0.32
    IonicModule
    -0.32
     format
    -0.32
    Personendaten
    -0.32
    POSITIVE LOGITS
     Italijani
    0.62
    ništvo
    0.60
    lgari
    0.59
    PyExc
    0.57
     EconPapers
    0.56
    >--}}
    0.56
    ivores
    0.56
     оригіналу
    0.56
    cipar
    0.55
     تضيفلها
    0.54
    Activations Density 0.149%

    No Known Activations