© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 6709
    Prev
    Next
    INDEX
    Explanations

    terms related to trends and metrics in research publications, particularly in the context of adolescent myopia prevention and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Improved
    -0.81
     Improved
    -0.80
     Enhanced
    -0.77
    Enhanced
    -0.76
    Improvements
    -0.74
    Improvement
    -0.73
     Improvement
    -0.73
    Improving
    -0.72
    improved
    -0.72
     Improving
    -0.71
    POSITIVE LOGITS
     incer
    0.56
     ince
    0.52
     inc
    0.47
     iner
    0.47
     dece
    0.40
     substantially
    0.39
    NVIC
    0.38
     concom
    0.38
    OCH
    0.37
    encre
    0.37
    Activations Density 0.549%

    No Known Activations