© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9499
    Prev
    Next
    INDEX
    Explanations

    indicators of economic conditions and related factors influencing the economy

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

    preceding "economy"

    np_acts-logits-general · gemini-2.0-flash

    economy

    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
     ujednoznacz
    -0.65
    ⓧ
    -0.59
    contentLoaded
    -0.58
     ddelweddau
    -0.57
    thral
    -0.56
    ThemeOverlay
    -0.53
     Archiproducts
    -0.52
    Vertical
    -0.51
    ept
    -0.50
    gebühren
    -0.50
    POSITIVE LOGITS
     economy
    2.21
     economic
    1.84
    economy
    1.77
     Economy
    1.73
    Economy
    1.68
     economies
    1.65
     ECONOMY
    1.64
     economia
    1.54
     economía
    1.50
    economic
    1.48
    Activations Density 0.176%

    No Known Activations