© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5990
    Prev
    Next
    INDEX
    Explanations

    references to 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.93
     FishBase
    -0.81
     jPanel
    -0.77
     Anfitrión
    -0.77
     dbo
    -0.74
    writeFieldEnd
    -0.73
    AndEndTag
    -0.73
    وأضاف
    -0.73
    voerd
    -0.73
    siębior
    -0.72
    POSITIVE LOGITS
     light
    3.96
     Light
    3.65
    light
    3.55
    Light
    3.54
     LIGHT
    3.34
    LIGHT
    3.05
     licht
    2.34
    lights
    2.27
     lights
    2.25
     lighter
    2.20
    Activations Density 0.055%

    No Known Activations