© 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. 37-GEMMASCOPE-RES-16K
    11. 4877
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their treatment, particularly focusing on cardiovascular diseases and autoimmune disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.63
     فريبيس
    -0.63
    ########.
    -0.60
    webElementXpaths
    -0.56
    ScopeManager
    -0.56
    PageContext
    -0.54
    ftagPool
    -0.52
     uLocal
    -0.51
    AutoModerator
    -0.51
    AccessorTable
    -0.50
    POSITIVE LOGITS
     disease
    2.08
     diseases
    1.80
    disease
    1.66
     Disease
    1.60
     illness
    1.59
     DISEASE
    1.55
     disorder
    1.48
    Disease
    1.48
    diseases
    1.44
     disorders
    1.42
    Activations Density 1.467%

    No Known Activations