© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8995
    Prev
    Next
    INDEX
    Explanations

    references and mentions of significant historical events or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.67
    EndInit
    -0.67
     localObject
    -0.66
    urlpatterns
    -0.65
    StoreMessageInfo
    -0.65
    complexType
    -0.63
    parsedMessage
    -0.61
     дописавши
    -0.61
     unknownFields
    -0.60
    MLLoader
    -0.59
    POSITIVE LOGITS
     globally
    0.66
     worldwide
    0.66
     global
    0.65
     international
    0.60
     world
    0.58
     weltweit
    0.58
     världen
    0.57
     mundial
    0.57
     globalization
    0.57
     Worldwide
    0.55
    Activations Density 0.405%

    No Known Activations