© 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. 21-GEMMASCOPE-RES-16K
    11. 2630
    Prev
    Next
    INDEX
    Explanations

    events and significant achievements related to a specific group or community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     démocr
    -0.98
     vœux
    -0.82
     vectorielles
    -0.73
     financières
    -0.68
     définiti
    -0.66
     genoux
    -0.66
     nuages
    -0.65
     sanitaires
    -0.64
     chré
    -0.62
     normaux
    -0.61
    POSITIVE LOGITS
     members
    1.37
     professionals
    1.35
     practitioners
    1.27
     participants
    1.26
     individuals
    1.26
     designers
    1.25
     leaders
    1.24
     fellows
    1.23
     experts
    1.23
     engineers
    1.22
    Activations Density 2.650%

    No Known Activations