Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12342
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to back pain and spine conditions

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

    back pain or injury

    np_acts-logits-general · gemini-2.0-flash

    lumbar pain and injury

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.86
     незавершена
    -0.76
    rrggbb
    -0.72
    yttö
    -0.68
    новништво
    -0.67
    énario
    -0.65
     AssemblyCulture
    -0.62
    Rhestr
    -0.61
    pantalla
    -0.61
    MemoryWarning
    -0.61
    POSITIVE LOGITS
     injury
    0.87
     Injury
    0.84
    Injury
    0.83
     pain
    0.78
    Injuries
    0.77
     injuries
    0.77
    injury
    0.77
     Injuries
    0.75
     injured
    0.74
     Pain
    0.72
    Activations Density 0.713%

    No Known Activations