© 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. 8376
    Prev
    Next
    INDEX
    Explanations

    terms related to Swaziland or variations of the word "Swazi."

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

    starting with "Sw" or "SW"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Sw

    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
    UnusedPrivate
    -0.74
    ContentAsync
    -0.72
    exitRule
    -0.68
    principalColumn
    -0.67
     NgModule
    -0.66
     يتيمه
    -0.66
     الحره
    -0.64
    styleType
    -0.63
    tableFuture
    -0.62
     useParams
    -0.62
    POSITIVE LOGITS
     Sw
    0.84
     sw
    0.84
    Sw
    0.83
    sw
    0.74
     SW
    0.69
    Swish
    0.67
     Swanson
    0.66
     Swar
    0.65
     Swa
    0.64
    SW
    0.64
    Activations Density 0.110%

    No Known Activations