© 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. 6121
    Prev
    Next
    INDEX
    Explanations

    specific string patterns or URL components in the text

    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
     lifestyle
    -0.29
     Lifestyle
    -0.29
     ناب
    -0.28
     CONSEQU
    -0.28
     Capability
    -0.27
     Gol
    -0.27
     Of
    -0.27
     cost
    -0.27
     Capa
    -0.26
    ಲು
    -0.26
    POSITIVE LOGITS
    ArgsConstructor
    0.78
     nahilalakip
    0.70
    EDEFAULT
    0.70
    IndentedString
    0.68
     Infórmanos
    0.68
     للمعارف
    0.67
    rungsseite
    0.67
     мәкал
    0.66
     indígen
    0.66
     autorytatywna
    0.66
    Activations Density 0.677%

    No Known Activations