© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15407
    Prev
    Next
    INDEX
    Explanations

    a mix of Arabic terms and references to specific geographical or cultural contexts

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

    Arabic text or Middle Eastern topics

    np_acts-logits-general · gemini-2.0-flash

    Arabian Peninsula and Middle East

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     ſte
    -0.58
     ſch
    -0.57
     itſelf
    -0.56
     tranſ
    -0.51
     تضيفلها
    -0.51
    лтамалар
    -0.49
     ſta
    -0.49
     pleaſure
    -0.49
    =#{
    -0.48
     viſ
    -0.47
    POSITIVE LOGITS
     Arabic
    0.54
     Arab
    0.52
    مقاله
    0.51
    مصادر
    0.49
     Saudi
    0.45
    Arab
    0.45
    توض
    0.45
    ARAB
    0.44
    emeni
    0.43
     Iraqi
    0.42
    Activations Density 0.190%

    No Known Activations