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. 130922
    Prev
    Next
    INDEX
    Explanations

    phrases indicating representation or speaking on behalf of others

    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
    liquez
    -0.41
     Newsletters
    -0.39
    Tub
    -0.38
     afbeeldingen
    -0.38
     narrowly
    -0.38
     basit
    -0.38
     toneladas
    -0.37
     delgada
    -0.37
     dramatically
    -0.37
     ſet
    -0.37
    POSITIVE LOGITS
     behalf
    0.65
    runApp
    0.56
     esternos
    0.53
    adaptiveStyles
    0.52
    Datuak
    0.52
    SPATH
    0.49
    IBOutlet
    0.48
     noDo
    0.48
     GoogleFonts
    0.48
     ModelExpression
    0.47
    Activations Density 0.034%

    No Known Activations