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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 73457
    Prev
    Next
    INDEX
    Explanations

    references to college and higher education

    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
    
    -0.73
    tagHelperRunner
    -0.60
    enterOuterAlt
    -0.59
     Ursache
    -0.59
     CURIAM
    -0.58
    ceptre
    -0.57
     InputDecoration
    -0.56
     noastre
    -0.55
     iż
    -0.54
     său
    -0.54
    POSITIVE LOGITS
     college
    0.90
     university
    0.76
    college
    0.70
    College
    0.70
     College
    0.69
     COLLEGE
    0.65
     universidad
    0.62
     colleges
    0.60
     University
    0.59
     universitarios
    0.57
    Activations Density 0.011%

    No Known Activations