© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 1238
    Prev
    Next
    INDEX
    Explanations

    terms related to optical measurements and physical properties of light

    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
    vician
    -0.40
    HomeAsUp
    -0.36
     whirlwind
    -0.36
     orologio
    -0.35
    tocin
    -0.35
    abinieri
    -0.35
    ariConfig
    -0.33
    WithMany
    -0.33
    rückt
    -0.32
    martre
    -0.32
    POSITIVE LOGITS
     scattering
    0.84
     refraction
    0.77
     Scattering
    0.73
    scattering
    0.71
     propagation
    0.71
     ray
    0.68
     attenuation
    0.68
     transmission
    0.66
     refra
    0.66
     transmit
    0.66
    Activations Density 1.001%

    No Known Activations