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. 114544
    Prev
    Next
    INDEX
    Explanations

    references to academic or honor societies

    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
    EDEFAULT
    -0.68
    AndEndTag
    -0.68
    ագրություններ
    -0.67
     createState
    -0.65
    хьтан
    -0.59
    ThroughAttribute
    -0.56
    Kaieteur
    -0.54
    nesium
    -0.54
     resourceCulture
    -0.53
    PropertyChanging
    -0.53
    POSITIVE LOGITS
     fraternity
    0.43
     Fraternity
    0.43
     roommates
    0.40
     Campus
    0.40
     college
    0.38
     campus
    0.38
     College
    0.37
     University
    0.33
     frater
    0.33
     Seek
    0.31
    Activations Density 0.005%

    No Known Activations