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. 22388
    Prev
    Next
    INDEX
    Explanations

    activities related to community engagement and local experiences

    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
     onBind
    -0.39
     Neff
    -0.35
     owes
    -0.35
    ždý
    -0.34
    moveToFirst
    -0.33
     indebted
    -0.33
    raff
    -0.33
     everywhere
    -0.33
    مقاله
    -0.33
    ערך
    -0.32
    POSITIVE LOGITS
    Rüyada
    0.59
    цездатний
    0.59
    IonicModule
    0.54
    ьаж
    0.52
     الرياضيه
    0.50
    WithMany
    0.50
    Diweddarwch
    0.49
    adaptiveStyles
    0.49
    reportWebVitals
    0.47
    EnableWeb
    0.47
    Activations Density 0.014%

    No Known Activations