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-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7292
    Prev
    Next
    INDEX
    Explanations

    structured data elements related to patient information in a medical context

    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
    PMailer
    -0.39
    ponses
    -0.39
    CompilerServices
    -0.38
     flight
    -0.37
     SDLK
    -0.37
    __*/
    -0.37
     scorpion
    -0.36
     BoxFit
    -0.36
     defStyle
    -0.36
     utafitiHapana
    -0.36
    POSITIVE LOGITS
     Encounter
    0.79
    Encounter
    0.75
    encounter
    0.73
     encounter
    0.71
     encounters
    0.70
     Encounters
    0.62
     HL
    0.60
     hl
    0.57
     Observations
    0.56
     encountered
    0.55
    Activations Density 0.300%

    No Known Activations