© 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. 18-GEMMASCOPE-RES-16K
    6. 10425
    Prev
    Next
    INDEX
    Explanations

    financial and commodity-related data, specifically focusing on exports and trading activity

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

    sales/commodities

    np_acts-logits-general · gemini-2.0-flash

    market price export

    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
    ValueStyle
    -0.58
     विश्वसनीयता
    -0.57
     autorytatywna
    -0.57
    oredCriteria
    -0.55
     المعيارى
    -0.55
    VersionUID
    -0.54
     Walkover
    -0.54
     OSS
    -0.54
    ποτε
    -0.54
     aDecoder
    -0.53
    POSITIVE LOGITS
     market
    0.81
     price
    0.77
     export
    0.77
     exporters
    0.73
     prices
    0.73
     buyers
    0.73
     markets
    0.71
     producers
    0.69
    market
    0.66
     exporter
    0.65
    Activations Density 0.142%

    No Known Activations