© 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. 8579
    Prev
    Next
    INDEX
    Explanations

    references to news articles and agency reports

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

    News agencies or reports

    np_acts-logits-general · gemini-2.0-flash

    news agencies

    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
    OpenHelper
    -0.51
     MotionEvent
    -0.50
     shadow
    -0.45
    مقال
    -0.45
     stop
    -0.45
    Portale
    -0.45
    mitt
    -0.44
     Bek
    -0.44
    личи
    -0.43
    Events
    -0.43
    POSITIVE LOGITS
     agency
    1.06
     Agencies
    1.04
     agencies
    1.00
     Agency
    0.97
     AGENCY
    0.93
     agences
    0.92
    Agencies
    0.90
     wires
    0.89
    agency
    0.89
    agencies
    0.89
    Activations Density 0.121%

    No Known Activations