© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104126
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical practices and healthcare facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.56
    Rüyada
    -0.45
     divertir
    -0.43
    grunns
    -0.41
    ="@+
    -0.40
    舺
    -0.40
     pubblici
    -0.40
    lusconi
    -0.39
    corazón
    -0.39
     beweging
    -0.38
    POSITIVE LOGITS
     specialist
    0.56
     consultation
    0.53
     specialists
    0.52
     staff
    0.52
    specialist
    0.49
     specialized
    0.47
     Consultation
    0.47
     Specialist
    0.46
     consult
    0.45
     referral
    0.44
    Activations Density 0.127%

    No Known Activations