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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5782
    Prev
    Next
    INDEX
    Explanations

    details related to dental professionals and their qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.82
    IntoConstraints
    -0.73
    setViewportView
    -0.63
    InitVars
    -0.63
     Италијани
    -0.61
    CloseOperation
    -0.60
     OFDb
    -0.59
    Xna
    -0.57
    
    -0.56
     torchvision
    -0.56
    POSITIVE LOGITS
     dental
    0.81
     tooth
    0.75
     teeth
    0.75
     Dental
    0.71
    Dental
    0.70
     dentist
    0.67
     Tooth
    0.65
    Tooth
    0.65
     dentistry
    0.64
     dentists
    0.62
    Activations Density 0.358%

    No Known Activations