© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8198
    Prev
    Next
    INDEX
    Explanations

    key culinary and dining experiences, particularly in relation to food markets and diverse dining options

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

    Businesses, shops, or establishments

    np_acts-logits-general · gemini-2.0-flash

    places being run or operated

    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
    出版年
    -0.94
     виправивши
    -0.82
    endforeach
    -0.71
    تقاوى
    -0.68
     snippetHide
    -0.68
    AutoScaleMode
    -0.67
    routeProvider
    -0.66
    findpost
    -0.65
    جغرافيا
    -0.64
     onResponse
    -0.64
    POSITIVE LOGITS
     staffed
    1.11
     located
    1.09
     operated
    1.07
     opened
    1.06
     run
    1.01
     offering
    1.00
     frequented
    0.98
     open
    0.96
     situated
    0.96
     manned
    0.87
    Activations Density 0.234%

    No Known Activations