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-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 58499
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibility and management roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.70
     alve
    -0.65
    commune
    -0.59
     geraten
    -0.59
     interferon
    -0.59
     viaj
    -0.56
     manifestazione
    -0.56
    hadiran
    -0.55
     exhibitors
    -0.55
     singularities
    -0.54
    POSITIVE LOGITS
     overseeing
    1.20
     oversee
    1.08
     responsible
    1.04
     handling
    0.95
     oversees
    0.95
    responsible
    0.93
     Overse
    0.91
     oversaw
    0.91
     responsibility
    0.90
     BoxDecoration
    0.89
    Activations Density 0.023%

    No Known Activations