© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2938
    Prev
    Next
    INDEX
    Explanations

    terms related to eye health and eye-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Solaris
    -0.59
     rând
    -0.56
    Scénario
    -0.56
     上下
    -0.56
    żdż
    -0.56
     ainfi
    -0.55
     morire
    -0.55
     naturellement
    -0.53
    seamnă
    -0.53
     Briggs
    -0.52
    POSITIVE LOGITS
     eye
    3.25
     Eye
    2.95
     EYE
    2.79
    Eye
    2.77
    eye
    2.74
    EYE
    2.45
     Ey
    1.82
     ey
    1.74
     ojo
    1.47
    Ey
    1.46
    Activations Density 0.056%

    No Known Activations