© 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. 18-GEMMASCOPE-RES-16K
    11. 1616
    Prev
    Next
    INDEX
    Explanations

    references to national debt and associated financial figures

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

    Numbers followed by "billion" or "trillion"

    np_acts-logits-general · gemini-2.0-flash

    billions and trillions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كورة
    -0.56
    thâu
    -0.56
    XmlType
    -0.54
     NUKAT
    -0.51
    XtraEditors
    -0.50
    enterOuterAlt
    -0.50
     Drapeau
    -0.47
     gele
    -0.47
    hql
    -0.47
    UrlResolution
    -0.46
    POSITIVE LOGITS
     billion
    1.02
     billions
    0.98
     trillion
    0.94
    billion
    0.78
     Milliarden
    0.72
     milliards
    0.72
     Billion
    0.71
    تقاوى
    0.71
     quadril
    0.68
     BrowserModule
    0.66
    Activations Density 0.208%

    No Known Activations