© 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. 16-GEMMASCOPE-RES-16K
    11. 7326
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before a conjunction or preposition

    np_acts-logits-general · gemini-2.0-flash

    Jackson, he, powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currently
    -0.85
     Currently
    -0.83
    currently
    -0.78
    Currently
    -0.78
     Wikiseite
    -0.77
     aujourd
    -0.75
     Cæsar
    -0.73
     derzeit
    -0.72
    aujourd
    -0.71
     actuellement
    -0.71
    POSITIVE LOGITS
     <>",
    0.79
     Мексичка
    0.63
     wireType
    0.62
     soon
    0.57
     propOrder
    0.56
    DeleteBehavior
    0.55
    RegistryLite
    0.55
     실패
    0.54
     later
    0.54
    この時期
    0.53
    Activations Density 1.083%

    No Known Activations