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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14624
    Prev
    Next
    INDEX
    Explanations

    terms related to "light"

    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
     chrétienne
    -0.66
     Bookmarks
    -0.66
     jPanel
    -0.65
    bobox
    -0.64
    iverr
    -0.63
    PreAuthorize
    -0.61
     Entomology
    -0.61
    ᾶ
    -0.61
     sirena
    -0.60
     estadual
    -0.60
    POSITIVE LOGITS
     light
    4.58
     Light
    3.99
    Light
    3.87
    light
    3.81
     LIGHT
    3.45
    LIGHT
    3.11
     lighter
    2.57
     licht
    2.46
     lightest
    2.27
     ligh
    2.00
    Activations Density 0.076%

    No Known Activations