© 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. 5-GEMMASCOPE-RES-16K
    11. 10789
    Prev
    Next
    INDEX
    Explanations

    situations involving sitting or lying down and the associated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.69
     lenker
    -0.66
    Datuak
    -0.61
    Искәрмәләр
    -0.61
     Vive
    -0.60
     paramString
    -0.57
     '\\;'
    -0.57
    UserScript
    -0.57
     חיצוניים
    -0.55
     impe
    -0.54
    POSITIVE LOGITS
    坐下
    0.85
     Seating
    0.81
     seating
    0.80
     chair
    0.80
     sentarse
    0.76
     seated
    0.75
     Chair
    0.75
     duduk
    0.75
     descansar
    0.74
    Chair
    0.72
    Activations Density 0.140%

    No Known Activations