© 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. 5866
    Prev
    Next
    INDEX
    Explanations

    frequency adverbs or expressions indicating time or recurrence

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

    time or frequency

    np_acts-logits-general · gemini-2.0-flash

    adverbs of frequency and time

    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
     purpoſe
    -0.77
     ſeveral
    -0.76
     Theſe
    -0.73
     chofe
    -0.73
     ſmall
    -0.68
     Monfieur
    -0.67
     uſe
    -0.66
    flüs
    -0.66
     greateſt
    -0.66
     himſelf
    -0.65
    POSITIVE LOGITS
     known
    0.77
     showing
    0.76
     called
    0.69
     requiring
    0.67
     allowing
    0.66
    showing
    0.65
     estimés
    0.64
     demonstrating
    0.62
     resulting
    0.62
    CloseOperation
    0.61
    Activations Density 0.271%

    No Known Activations