© 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. 16-GEMMASCOPE-RES-16K
    11. 4917
    Prev
    Next
    INDEX
    Explanations

    mentions of light sources and illumination concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "light" and "lighting"

    np_acts-logits-general · gemini-2.0-flash

    light and illumination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    floxacin
    -0.80
     bezeichneter
    -0.77
    RegistryLite
    -0.74
     propOrder
    -0.73
     محفوظة
    -0.73
     viewType
    -0.72
    ptonshire
    -0.70
    WriteAttribute
    -0.69
    ajuku
    -0.68
     оригіналу
    -0.68
    POSITIVE LOGITS
     lights
    1.22
     LIGHT
    1.18
     Light
    1.14
     Lights
    1.08
    LIGHT
    1.07
     lighting
    1.06
    Light
    1.06
    Lighting
    1.04
    light
    1.04
     light
    1.03
    Activations Density 0.151%

    No Known Activations