© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 10137
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to ophthalmology and eye conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.42
     clavic
    -0.38
    }{*}{}
    -0.33
     engines
    -0.32
    AccessorTable
    -0.32
    complexContent
    -0.31
    WireFormatLite
    -0.31
    orElse
    -0.30
     engine
    -0.30
     defaultstate
    -0.30
    POSITIVE LOGITS
     eye
    1.17
     retina
    1.15
     Eye
    1.15
     retinal
    1.14
    Eye
    1.06
     ophthal
    1.05
    eye
    1.04
     EYE
    1.04
     eyeball
    0.99
     Retina
    0.98
    Activations Density 0.517%

    No Known Activations