© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 6538
    Prev
    Next
    INDEX
    Explanations

    elements related to cars and the automotive industry

    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
     critères
    -0.70
     pescoço
    -0.68
     conférence
    -0.67
     nôtre
    -0.67
     beroep
    -0.66
     fidélité
    -0.65
     seuls
    -0.64
     malheure
    -0.62
     brancas
    -0.62
     personnalité
    -0.62
    POSITIVE LOGITS
     masterpiece
    1.19
     gem
    1.06
     behe
    1.02
     wonder
    1.01
     masterpieces
    0.98
     marvel
    0.96
     beauties
    0.94
     marvels
    0.93
     delight
    0.92
     gems
    0.92
    Activations Density 0.326%

    No Known Activations