© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3857
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and entities, particularly in relation to Qatar and its activities

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

    Qatar

    np_acts-logits-general · gemini-2.0-flash

    Qatar and Doha

    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
     متعلقه
    -0.72
    MessageOf
    -0.67
    enderror
    -0.60
     Référence
    -0.60
    ReusableCell
    -0.55
    ClassLoader
    -0.55
    sizeCache
    -0.54
    AndroidJUnit
    -0.53
     Yosemite
    -0.52
     Bant
    -0.52
    POSITIVE LOGITS
     Qatar
    1.35
     Doha
    1.28
    Doha
    1.21
    Qatar
    1.15
     qatar
    0.91
    🇶
    0.87
     قطر
    0.81
     QR
    0.77
     Q
    0.72
     QL
    0.71
    Activations Density 0.157%

    No Known Activations