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. 22392
    Prev
    Next
    INDEX
    Explanations

    contexts related to uncertainty, expectations, and unfulfilled anticipations

    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
    KommentareTeilen
    -0.73
    PhysRevD
    -0.61
     nahilalakip
    -0.55
     surla
    -0.52
    parsedMessage
    -0.49
    PhysRev
    -0.48
     uska
    -0.48
    pired
    -0.47
     Зак
    -0.47
    ismet
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    0.38
     uncontrollable
    0.36
     unforeseen
    0.35
     impré
    0.33
    mybatisplus
    0.32
     fly
    0.32
    无法
    0.31
     indépendant
    0.30
     onge
    0.30
     trattano
    0.30
    Activations Density 0.065%

    No Known Activations