© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 11733
    Prev
    Next
    INDEX
    Explanations

    references to ownership and relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.86
     autorytatywna
    -0.85
    ValueStyle
    -0.83
    httphttps
    -0.81
     Chwiliwch
    -0.79
     للاسماء
    -0.78
     AssemblyTitle
    -0.74
     surla
    -0.71
     tartalomajánló
    -0.71
    richTextPanel
    -0.71
    POSITIVE LOGITS
     own
    0.52
     propria
    0.41
     propia
    0.38
     sendiri
    0.37
     propias
    0.36
     exemplaire
    0.35
    Own
    0.35
     royaume
    0.34
     selber
    0.33
     自己
    0.33
    Activations Density 0.621%

    No Known Activations