© 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. 7474
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements related to dimensions and values in scientific contexts

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

    Units of measure (nm, eV, cm, ppm, mm, mg, liters)

    np_acts-logits-general · gemini-2.0-flash

    units and measurements

    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
    曖昧さ回避
    -0.89
     BoxDecoration
    -0.82
    tagHelperRunner
    -0.79
    transQ
    -0.78
     يتيمه
    -0.76
    WebElementEntity
    -0.74
    =$?
    -0.69
     كومونز
    -0.67
     дописавши
    -0.67
     تضيفلها
    -0.67
    POSITIVE LOGITS
    左右
    0.61
    .,
    0.55
    pbs
    0.54
    /~
    0.53
    
    0.50
    /$
    0.49
     minimum
    0.49
     तक
    0.49
    JdbcTemplate
    0.48
     vechi
    0.48
    Activations Density 0.715%

    No Known Activations