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. 18-GEMMASCOPE-RES-16K
    6. 10278
    Prev
    Next
    INDEX
    Explanations

    terms related to vision and eye health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPATH
    -0.75
    ConstraintMaker
    -0.57
    djangoproject
    -0.55
    WebVitals
    -0.52
    wikidata
    -0.51
    ônimo
    -0.49
    Carlton
    -0.48
    CodedInputStream
    -0.48
     StatefulWidget
    -0.47
    GeoNames
    -0.47
    POSITIVE LOGITS
     vision
    1.68
     Vision
    1.48
     visibility
    1.46
    Vision
    1.39
     VISION
    1.38
    vision
    1.36
     eyesight
    1.29
     Visibility
    1.25
    VISION
    1.22
     blindness
    1.21
    Activations Density 0.265%

    No Known Activations