© 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. 20-GEMMASCOPE-RES-16K
    11. 3571
    Prev
    Next
    INDEX
    Explanations

    instances of sports-related injuries

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

    Preceding words of injuries

    np_acts-logits-general · gemini-2.0-flash

    physical injuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.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
    tagHelperRunner
    -0.58
     تضيفلها
    -0.56
    AddAttribute
    -0.56
     AIDS
    -0.53
     parallelism
    -0.51
    cheln
    -0.51
    verwijspagina
    -0.50
     utafitiHapana
    -0.50
    AIDS
    -0.49
    ChildScrollView
    -0.48
    POSITIVE LOGITS
     broken
    0.90
     fractured
    0.89
     injuries
    0.89
     fractures
    0.82
     injury
    0.78
    broken
    0.76
     ruptured
    0.74
     fracturing
    0.74
     torn
    0.73
     Injuries
    0.73
    Activations Density 0.222%

    No Known Activations