Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 73541
    Prev
    Next
    INDEX
    Explanations

    mentions of medical or professional conferences and associated activities

    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
     typelib
    -0.58
    addContainerGap
    -0.44
     votación
    -0.44
    mybatisplus
    -0.42
     Réponses
    -0.42
    quake
    -0.41
    الحياه
    -0.41
     دیکھیے
    -0.41
    extAlignment
    -0.40
     promesa
    -0.40
    POSITIVE LOGITS
     patient
    0.61
    patient
    0.55
     patients
    0.54
     clinical
    0.52
     Clinical
    0.50
    期刊论文
    0.50
     Patient
    0.49
    Patient
    0.49
     clinically
    0.49
     Patients
    0.47
    Activations Density 0.103%

    No Known Activations