© 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. 13663
    Prev
    Next
    INDEX
    Explanations

    references to ethnic demographics and statistical ownership

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

    accounting or proportions

    np_acts-logits-general · gemini-2.0-flash

    account for percentages or quantities

    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
     архивлан
    -0.51
    enderror
    -0.51
    RegistryLite
    -0.48
    ValueStyle
    -0.45
     arşivlendi
    -0.45
    lizia
    -0.44
    wpi
    -0.43
    simpleType
    -0.42
    ary
    -0.42
    ConverterFactory
    -0.41
    POSITIVE LOGITS
     accounted
    1.93
     account
    1.77
     accounts
    1.76
     accounting
    1.68
    account
    1.57
     ACCOUNT
    1.55
     Account
    1.54
    accounting
    1.54
    accounts
    1.49
     constitute
    1.49
    Activations Density 0.572%

    No Known Activations