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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1351
    Prev
    Next
    INDEX
    Explanations

    phrases related to scheduling and providing updates

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

    Announcements or updates

    np_acts-logits-general · gemini-2.0-flash

    updates and information coming soon

    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
     HasFactory
    -0.77
    featureID
    -0.75
    Autoritní
    -0.72
    URLException
    -0.70
    IsMutable
    -0.69
    kháu
    -0.69
     незавершена
    -0.69
    WebVitals
    -0.68
     Meksiku
    -0.66
    Diweddarwch
    -0.65
    POSITIVE LOGITS
     updates
    1.18
    Stay
    1.06
     Stay
    1.04
     stay
    1.03
     Updates
    0.99
    Updates
    0.96
    stay
    0.95
    updates
    0.95
     update
    0.84
     UPDATES
    0.80
    Activations Density 0.143%

    No Known Activations