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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 4385
    Prev
    Next
    INDEX
    Explanations

    specific terms related to viral infections and their effects in livestock

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

    pigs, swine, or pork

    np_acts-logits-general · gemini-2.0-flash

    animal husbandry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.69
    ValueStyle
    -0.67
    TintMode
    -0.60
    kháu
    -0.56
    BeginContext
    -0.54
     glaciers
    -0.52
    emples
    -0.52
    GEBURTSDATUM
    -0.51
     Xerox
    -0.51
     climbers
    -0.51
    POSITIVE LOGITS
     pig
    0.91
     pigs
    0.88
     slaughter
    0.87
     swine
    0.85
     feed
    0.85
     pork
    0.84
     rearing
    0.80
     Pigs
    0.77
     broiler
    0.76
     Pork
    0.75
    Activations Density 0.384%

    No Known Activations