© 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. 9414
    Prev
    Next
    INDEX
    Explanations

    references to people and organizations involved in medical or charitable work

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

    Capitalized words and place names

    np_acts-logits-general · gemini-2.0-flash

    Cornish 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
    leswig
    -0.56
    MigrationBuilder
    -0.56
     Chiba
    -0.53
     eggplant
    -0.50
    íslu
    -0.50
     Hamburger
    -0.50
     esophageal
    -0.50
    XmlAccessorType
    -0.49
     千葉
    -0.48
     Elke
    -0.48
    POSITIVE LOGITS
     Cornwall
    1.08
     Cornish
    0.95
    Corn
    0.86
     Plymouth
    0.75
     Falmouth
    0.73
     CORN
    0.70
     Gwen
    0.69
     Tru
    0.69
     Devon
    0.68
     Ker
    0.67
    Activations Density 0.086%

    No Known Activations