© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7028
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.59
    Bowling
    -0.56
    Skate
    -0.56
     Coaches
    -0.54
     Skate
    -0.54
     Wrestle
    -0.54
    eradish
    -0.53
    Race
    -0.53
     Race
    -0.52
    Coach
    -0.52
    POSITIVE LOGITS
     sport
    1.12
     sports
    1.08
     sporting
    0.97
     professional
    0.82
    sport
    0.76
     olahraga
    0.68
    sports
    0.68
     esporte
    0.66
     deportes
    0.64
    professional
    0.61
    Activations Density 0.267%

    No Known Activations