© 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. 8069
    Prev
    Next
    INDEX
    Explanations

    questions and conversions involving measurements

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

    Measurement units following "in" or "of"

    np_acts-logits-general · gemini-2.0-flash

    units of measurement

    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
    thâu
    -0.49
    :✨
    -0.49
    rdom
    -0.49
    shadowOffset
    -0.48
    sitions
    -0.46
    formik
    -0.45
    MessageTagHelper
    -0.44
    adata
    -0.41
    owieck
    -0.41
     delegado
    -0.41
    POSITIVE LOGITS
     units
    1.43
     Units
    1.18
     unit
    1.16
    units
    1.13
     UNITS
    1.13
     milli
    1.08
     kilogram
    1.04
    Units
    1.03
     kilograms
    1.03
    millimeters
    1.02
    Activations Density 0.806%

    No Known Activations