© 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. 20-GEMMASCOPE-RES-16K
    11. 15793
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of female representation in media or society

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

    ending in "ently", "ally", "ens"

    np_acts-logits-general · gemini-2.0-flash

    word endings and common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.66
    Спасылкі
    -0.59
     quæ
    -0.59
    PhysRevD
    -0.59
    latego
    -0.58
     abstrait
    -0.57
    PerformLayout
    -0.57
    jspx
    -0.57
     StatelessWidget
    -0.57
     Constitucional
    -0.57
    POSITIVE LOGITS
    :✨
    0.81
     चीज़ों
    0.63
    دانشنامهٔ
    0.63
     kasarigan
    0.63
    ItemBackground
    0.59
    IsContent
    0.58
     spake
    0.56
     dúvidas
    0.56
    enschappelijke
    0.53
    DeleteBehavior
    0.51
    Activations Density 0.658%

    No Known Activations