© 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. 22-GEMMASCOPE-RES-16K
    11. 7441
    Prev
    Next
    INDEX
    Explanations

    references to time periods and the impact of specific events or developments

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

    Preceding past-tense verbs

    np_acts-logits-general · gemini-2.0-flash

    auxiliary have and has

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.72
     kaarangay
    -0.68
     disambiguazione
    -0.68
     propOrder
    -0.67
     Wiktionnaire
    -0.62
    =$?
    -0.61
    /**
    -0.59
    Gön
    -0.57
    addContainerGap
    -0.57
    #
    -0.56
    POSITIVE LOGITS
     has
    2.43
     have
    2.09
     telah
    2.00
    has
    1.93
    Has
    1.87
     đã
    1.76
     Has
    1.74
     Have
    1.62
    have
    1.55
    Have
    1.55
    Activations Density 1.965%

    No Known Activations