© 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. 10570
    Prev
    Next
    INDEX
    Explanations

    references to timing measurements or delays in milliseconds

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

    Units of time (milliseconds, microseconds, nanoseconds)

    np_acts-logits-general · gemini-2.0-flash

    units of time

    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
    RegressionTest
    -0.66
    cinoma
    -0.57
     CURIAM
    -0.53
    !*\
    -0.52
    깥
    -0.52
    Garth
    -0.51
    SPOT
    -0.50
    siren
    -0.48
     typelib
    -0.48
    ographique
    -0.48
    POSITIVE LOGITS
     milliseconds
    1.08
     micro
    1.06
     ms
    1.02
    ms
    0.98
     nano
    0.92
     msec
    0.89
    micro
    0.89
    Micro
    0.88
     milli
    0.84
     MICRO
    0.83
    Activations Density 0.565%

    No Known Activations