Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13420
    Prev
    Next
    INDEX
    Explanations

    references to economic conditions and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشارکت‌کنندگان
    -0.55
    AttributeSet
    -0.54
    ⓧ
    -0.52
     nakalista
    -0.50
    columnNumber
    -0.48
     Municipalidad
    -0.48
    šnje
    -0.48
     ujednoznacz
    -0.47
     Xamarin
    -0.47
    uría
    -0.47
    POSITIVE LOGITS
     economy
    2.61
     economic
    2.47
     Economy
    2.19
    economy
    2.18
    economic
    2.09
    Economy
    2.07
     Economic
    1.99
     ECONOMY
    1.98
    Economic
    1.94
     economies
    1.94
    Activations Density 0.186%

    No Known Activations