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-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 13001
    Prev
    Next
    INDEX
    Explanations

    specific medical terms and references related to conditions, trends, and classifications, particularly in relation to respiratory distress and mechanical ventilation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zij
    -0.80
     Seton
    -0.78
    kaido
    -0.77
    endphp
    -0.76
    Hozzáférés
    -0.75
    {~
    -0.74
     Seif
    -0.73
     Sepp
    -0.73
     autorisation
    -0.72
    قط
    -0.70
    POSITIVE LOGITS
     KRA
    0.95
     GRA
    0.87
     createSprite
    0.83
     Cram
    0.80
     Kraw
    0.80
     Kram
    0.80
     CRC
    0.79
     DRA
    0.78
     CRU
    0.77
     kras
    0.77
    Activations Density 0.931%

    No Known Activations