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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 7469
    Prev
    Next
    INDEX
    Explanations

    contexts related to legal or procedural actions, especially those involving stops and pauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Források
    -0.53
    dibles
    -0.52
    getRequest
    -0.48
     drives
    -0.48
    missie
    -0.48
     Navarra
    -0.47
     Drive
    -0.46
     drive
    -0.45
    interop
    -0.45
    LEADING
    -0.44
    POSITIVE LOGITS
     standstill
    0.81
    Stayed
    0.79
    SourceChecksum
    0.74
    stationary
    0.74
     zatrzy
    0.73
     settle
    0.73
    躇
    0.73
     Paused
    0.73
     pause
    0.73
     dừng
    0.72
    Activations Density 0.344%

    No Known Activations