© 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. 33-GEMMASCOPE-RES-16K
    11. 381
    Prev
    Next
    INDEX
    Explanations

    sentences with emotional and impactful expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -1.02
    httphttps
    -0.96
     kaarangay
    -0.95
    parsedMessage
    -0.93
    rungsseite
    -0.92
     Италијани
    -0.91
     nakalista
    -0.91
    GEBURTSDATUM
    -0.91
    Diweddarwch
    -0.89
     الرياضيه
    -0.87
    POSITIVE LOGITS
     Lastly
    0.94
    Lastly
    0.93
    Finally
    0.90
     Finally
    0.87
    总之
    0.81
     lastly
    0.75
     infine
    0.72
     finally
    0.70
     finalmente
    0.61
     enfin
    0.60
    Activations Density 0.984%

    No Known Activations