© 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. 14212
    Prev
    Next
    INDEX
    Explanations

    references to legal or evidentiary processes in a criminal context

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

    estimation or approximation

    np_acts-logits-general · gemini-2.0-flash

    estimating or stating approximate values

    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
     format
    -0.44
     pay
    -0.44
    paying
    -0.43
     paying
    -0.43
     Pay
    -0.42
     Normal
    -0.42
    uland
    -0.42
     PAY
    -0.42
    Pay
    -0.41
     melayani
    -0.41
    POSITIVE LOGITS
     estimate
    1.54
     estimates
    1.52
     estimated
    1.46
     estimating
    1.40
     estimation
    1.37
     Estimates
    1.36
    Estimates
    1.34
     estimations
    1.26
     estimat
    1.23
     Estimate
    1.23
    Activations Density 0.563%

    No Known Activations