© 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-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15177
    Prev
    Next
    INDEX
    Explanations

    specific names and terms in different languages, particularly focusing on people's names, place names, and party affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.82
     propOrder
    -0.71
    oa̍t
    -0.68
    تقاوى
    -0.66
    ftagPool
    -0.62
     Мексичка
    -0.60
    AsUp
    -0.60
    transQ
    -0.57
    Geplaatst
    -0.57
     referenties
    -0.56
    POSITIVE LOGITS
     colombiano
    0.58
     Colombian
    0.55
     colombiana
    0.53
     Colombia
    0.47
     Karnataka
    0.47
     Bandung
    0.46
     Kannada
    0.45
     Sarajevo
    0.43
    Colombia
    0.43
    tcl
    0.41
    Activations Density 1.270%

    No Known Activations