© 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. 18-GEMMASCOPE-RES-16K
    11. 1859
    Prev
    Next
    INDEX
    Explanations

    references to diversity and inclusion across different racial and ethnic backgrounds

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

    Comes after "from," "diverse," or describes backgrounds

    np_acts-logits-general · gemini-2.0-flash

    diverse backgrounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cipolla
    -0.49
    ésia
    -0.45
    uté
    -0.45
    ciful
    -0.43
    astricht
    -0.43
    autogui
    -0.42
    CreateIndex
    -0.42
    รวม
    -0.42
     virtuales
    -0.42
     Verantwort
    -0.41
    POSITIVE LOGITS
     backgrounds
    1.86
     background
    1.82
     Background
    1.61
     BACKGROUND
    1.50
    background
    1.49
    Background
    1.48
    BACKGROUND
    1.35
     latar
    1.20
    背景
    1.17
     achtergrond
    1.16
    Activations Density 0.179%

    No Known Activations