© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 115576
    Prev
    Next
    INDEX
    Explanations

    terms related to injuries and their effects, particularly regarding the elbow joint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    physical pain and injuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tes
    -0.34
    べて
    -0.32
     han
    -0.28
     dates
    -0.27
    wirtschaft
    -0.26
     ir
    -0.26
    Date
    -0.26
     цвет
    -0.26
    Havolalar
    -0.26
     Han
    -0.25
    POSITIVE LOGITS
     pinulongan
    0.66
    romyalgia
    0.62
     transfieras
    0.59
     الرياضيه
    0.59
     ſehr
    0.59
     ſeinem
    0.57
    niſſe
    0.57
     dieſem
    0.57
     beſch
    0.57
    Injuries
    0.57
    Activations Density 0.023%

    No Known Activations