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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129870
    Prev
    Next
    INDEX
    Explanations

    references to herpes viruses, particularly in a medical or scientific context

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

    herpes simplex virus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лтемелер
    -0.41
     pulmonar
    -0.40
    ApiModel
    -0.40
     везе
    -0.39
     GenerationType
    -0.38
     indisponible
    -0.37
     تضيفلها
    -0.35
    comuna
    -0.34
    どき
    -0.34
    VersionUID
    -0.32
    POSITIVE LOGITS
     Herpes
    0.94
     herpes
    0.94
     HSV
    0.89
    HSV
    0.75
     shingles
    0.73
     simplex
    0.66
    tagHelperRunner
    0.64
     blisters
    0.62
    Her
    0.61
     antiviral
    0.61
    Activations Density 0.080%

    No Known Activations