© 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. 10-GEMMASCOPE-RES-16K
    11. 12002
    Prev
    Next
    INDEX
    Explanations

    references to the incorporation of concepts or elements into various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     honte
    -0.71
    россий
    -0.66
     dignité
    -0.66
     blanches
    -0.65
     attestation
    -0.64
     croire
    -0.61
     américain
    -0.61
     LoggerFactory
    -0.60
     Monfieur
    -0.60
    onActivityResult
    -0.60
    POSITIVE LOGITS
     incorporate
    1.28
     incorporating
    1.20
     Incorpor
    1.17
     incorporates
    1.17
     incorporated
    1.10
     incorporation
    1.08
     Incorporation
    1.02
     inclusion
    0.99
     INCORPOR
    0.97
    incorpor
    0.94
    Activations Density 0.419%

    No Known Activations