© 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. 8545
    Prev
    Next
    INDEX
    Explanations

    phrases related to community impact and participation

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

    Location after "in," "across," or "around."

    np_acts-logits-general · gemini-2.0-flash

    prepositions followed by place names

    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
    WireFormatLite
    -0.67
     ſind
    -0.65
     linkovi
    -0.62
    ayuno
    -0.60
    PreferredItem
    -0.59
    hynch
    -0.58
    yntaxException
    -0.57
    UnusedPrivate
    -0.56
    DoubleQuotes
    -0.55
    MigrationBuilder
    -0.55
    POSITIVE LOGITS
     Manitoba
    1.03
     Saskatchewan
    1.01
     Singapore
    0.96
     Ontario
    0.95
     Saskatoon
    0.93
     Queensland
    0.93
     Australian
    0.93
     Texas
    0.93
     Toronto
    0.92
     Calgary
    0.91
    Activations Density 1.670%

    No Known Activations