© 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. 9954
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating quantities or proportions

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

    Numbers following "more than" or "over"

    np_acts-logits-general · gemini-2.0-flash

    more than numbers

    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
     EconPapers
    -0.97
     beginnetje
    -0.94
     <=",
    -0.87
    IndentedString
    -0.85
     للمعارف
    -0.85
    thâu
    -0.82
    Portale
    -0.81
    MessageTagHelper
    -0.81
    EndGlobalSection
    -0.79
    Geplaatst
    -0.78
    POSITIVE LOGITS
     half
    0.90
     eight
    0.81
     six
    0.80
     twenty
    0.78
     seven
    0.77
     three
    0.77
     two
    0.77
     five
    0.76
     thirty
    0.75
     four
    0.72
    Activations Density 0.122%

    No Known Activations