© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5424
    Prev
    Next
    INDEX
    Explanations

    key concepts related to ecology and environmental science

    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
    astify
    -0.78
     dépens
    -0.63
     étrang
    -0.62
     élevés
    -0.62
     réguli
    -0.61
     chré
    -0.61
     reconnu
    -0.61
     définiti
    -0.60
     leçon
    -0.60
     connus
    -0.60
    POSITIVE LOGITS
     size
    0.82
     performance
    0.79
     characteristics
    0.73
     quality
    0.69
     performances
    0.63
     sizes
    0.62
     parameters
    0.62
     types
    0.61
     effectiveness
    0.60
     properties
    0.60
    Activations Density 1.530%

    No Known Activations