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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 28181
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even" used in various contexts, especially emphasizing contrast or unexpectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     EconPapers
    -0.59
     iconLine
    -0.49
    routeProvider
    -0.49
    getSystemService
    -0.47
     دیکھیے
    -0.47
    UserScript
    -0.47
    adaptiveStyles
    -0.46
    }{*}{}
    -0.43
    UnusedPrivate
    -0.42
     interlocutor
    -0.42
    POSITIVE LOGITS
    perhaps
    0.62
     perhaps
    0.57
     quizá
    0.56
    GEBURTS
    0.54
    maybe
    0.54
     maybe
    0.51
     mungkin
    0.46
    PMailer
    0.46
     talvez
    0.45
     possibly
    0.44
    Activations Density 0.017%

    No Known Activations