© 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. 11347
    Prev
    Next
    INDEX
    Explanations

    evaluative language related to experiences

    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
     currently
    -0.99
     atualmente
    -0.90
     attualmente
    -0.87
     actualmente
    -0.85
    currently
    -0.85
     presently
    -0.85
     obecnie
    -0.85
     actuellement
    -0.85
     derzeit
    -0.81
     Currently
    -0.80
    POSITIVE LOGITS
     was
    0.83
    楽しかった
    0.82
     Overall
    0.75
    Overall
    0.73
    面白かった
    0.71
    Highlights
    0.71
     overall
    0.70
     пришлось
    0.68
     ended
    0.66
     despite
    0.66
    Activations Density 0.800%

    No Known Activations