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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 1803
    Prev
    Next
    INDEX
    Explanations

    terminology related to low back pain and associated medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.79
    tvguidetime
    -0.71
     المعيارى
    -0.64
     muualla
    -0.63
    kheim
    -0.62
    Obrázky
    -0.61
     اكتوبر
    -0.59
    nextDouble
    -0.59
    dima
    -0.59
    tillation
    -0.59
    POSITIVE LOGITS
     injury
    0.63
     ortop
    0.63
     injuries
    0.60
     orthopedic
    0.60
    Injury
    0.59
     articula
    0.59
     tendons
    0.58
     ergonom
    0.56
     трав
    0.56
     musculoskeletal
    0.56
    Activations Density 0.419%

    No Known Activations