© 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. 13699
    Prev
    Next
    INDEX
    Explanations

    instances of numbers and mathematical quantities

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

    Numbers around 100, 1000, or percentages

    np_acts-logits-general · gemini-2.0-flash

    per 100,000

    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
    queryInterface
    -0.64
     Himo
    -0.62
    tonsoft
    -0.59
     estimés
    -0.57
    oker
    -0.57
     culturelles
    -0.56
     resourceCulture
    -0.56
    Rüyada
    -0.55
    ioen
    -0.53
     chargés
    -0.53
    POSITIVE LOGITS
     thousand
    1.44
     hundred
    1.31
    thousand
    1.25
    Thousand
    1.17
     Thousand
    1.13
     thousands
    1.11
     THOUS
    1.10
    hundred
    1.09
     Hundred
    1.07
    Hundred
    1.06
    Activations Density 0.498%

    No Known Activations