© 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. 8627
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships and functions involving variables

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

    Greater than/less than mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    comparison operators

    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
     MainAxisSize
    -0.67
    InputBorder
    -0.67
    الحياه
    -0.61
    Hauptartikel
    -0.59
    ANTLR
    -0.58
    شهاد
    -0.58
    новниш
    -0.58
    .*")]
    -0.57
    tagHelperRunner
    -0.56
    ništvo
    -0.55
    POSITIVE LOGITS
     >
    1.97
     <
    1.88
    >
    1.69
    <
    1.64
     $>
    1.52
     >=
    1.50
     greater
    1.48
    }>
    1.48
     $<
    1.45
     ≥
    1.42
    Activations Density 2.282%

    No Known Activations