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

    Neuronpedia

    Jacobian LensNEW
    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. 6181
    Prev
    Next
    INDEX
    Explanations

    Arabic words or phrases

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

    Arabic text and potentially other right-to-left languages

    np_acts-logits-general · gemini-2.0-flash

    Jabal Omar locations

    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
     recev
    -0.67
     européens
    -0.65
     vertes
    -0.62
    be
    -0.62
     gouvernements
    -0.61
     africains
    -0.61
     aient
    -0.60
     démocr
    -0.59
     adulte
    -0.59
     spagnolo
    -0.58
    POSITIVE LOGITS
     يتيمه
    1.03
    بوابة
    0.72
    dafx
    0.71
     iprot
    0.70
    المناصب
    0.68
    DotNetBar
    0.63
     محفوظة
    0.63
    sizeCache
    0.62
    makeConstraints
    0.61
    "}")
    0.59
    Activations Density 0.003%

    No Known Activations