© 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-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7431
    Prev
    Next
    INDEX
    Explanations

    medical terms and diagnoses related to patient cases

    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
     sapiens
    -0.50
    approach
    -0.47
    onOptions
    -0.45
    Footnotes
    -0.44
    áctica
    -0.44
    BagLayout
    -0.43
    творення
    -0.42
     sessionFactory
    -0.41
    omla
    -0.41
    ління
    -0.41
    POSITIVE LOGITS
     scan
    0.85
     tests
    0.85
     scans
    0.80
     examinations
    0.80
     scanning
    0.79
    stest
    0.79
     exams
    0.78
     examination
    0.75
     screenings
    0.75
     test
    0.74
    Activations Density 0.659%

    No Known Activations