© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 7317
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to symptoms and 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
    ExecuteReader
    -0.44
     публи
    -0.42
     opérations
    -0.42
    setVerticalGroup
    -0.42
     biologists
    -0.41
     pinulongan
    -0.41
     chercheurs
    -0.40
     débats
    -0.38
    ynchrotron
    -0.38
    bership
    -0.38
    POSITIVE LOGITS
     client
    0.75
     patient
    0.71
     klien
    0.71
    Patient
    0.68
     Patient
    0.68
    patient
    0.66
     Client
    0.64
     clients
    0.62
    client
    0.62
     Clients
    0.62
    Activations Density 1.343%

    No Known Activations