© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6432
    Prev
    Next
    INDEX
    Explanations

    terms related to illumination and light in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tobi
    -0.54
    principalColumn
    -0.53
     Pogba
    -0.48
    իս
    -0.47
    strateg
    -0.47
     drôle
    -0.47
    Autoritní
    -0.47
     Mille
    -0.46
    thmus
    -0.46
     idéia
    -0.46
    POSITIVE LOGITS
     illumination
    1.58
     illuminated
    1.48
     illuminate
    1.46
     brightness
    1.44
     Illumination
    1.41
     illuminates
    1.40
     shine
    1.40
    illumin
    1.39
     glow
    1.37
     illumin
    1.35
    Activations Density 2.475%

    No Known Activations