© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 16017
    Prev
    Next
    INDEX
    Explanations

    references to experimental conditions related to prolonged incubation times in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.72
    $_['
    -0.62
    !</
    -0.60
    AccessorTable
    -0.59
    Diweddarwch
    -0.58
    AutoresizingMask
    -0.58
     CURIAM
    -0.56
    ChildScrollView
    -0.55
    </caption>
    -0.54
     חיצוניים
    -0.54
    POSITIVE LOGITS
    vernight
    0.77
     overnight
    0.73
    WithIOException
    0.71
     Overnight
    0.69
    Overnight
    0.65
    renewcommand
    0.64
    Scrap
    0.64
     throats
    0.63
     scrap
    0.60
    voa
    0.58
    Activations Density 0.974%

    No Known Activations