© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 10555
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conflicting emotions or contrasting ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     therefore
    -0.86
    therefore
    -0.80
     sice
    -0.78
     zwar
    -0.78
    จึง
    -0.74
     hence
    -0.72
    hence
    -0.71
    λοι
    -0.70
     portanto
    -0.70
    thus
    -0.66
    POSITIVE LOGITS
     nonetheless
    1.00
    却被
    0.99
     ändå
    0.97
    卻
    0.96
     nevertheless
    0.96
    却
    0.96
     digress
    0.95
     lại
    0.95
    却没有
    0.92
    一方で
    0.90
    Activations Density 0.696%

    No Known Activations