© 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. 9-GEMMASCOPE-RES-16K
    11. 11374
    Prev
    Next
    INDEX
    Explanations

    instances of the word "yet" indicating contrast or an unexpected outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ESPEC
    -0.34
     pungkasnya
    -0.33
     malin
    -0.31
    /***/
    -0.30
     sortes
    -0.30
     خاطر
    -0.30
    #
    -0.30
     først
    -0.29
    Biografia
    -0.29
     especialmente
    -0.29
    POSITIVE LOGITS
     nevertheless
    1.03
    etheless
    1.02
     nonetheless
    1.01
    Yet
    1.00
     Pourtant
    1.00
     Yet
    1.00
     Trotzdem
    0.98
    Nevertheless
    0.98
     Nevertheless
    0.96
     pourtant
    0.95
    Activations Density 0.246%

    No Known Activations