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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 16013
    Prev
    Next
    INDEX
    Explanations

    terms related to economic conditions and activities

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

    "economic" or "economy"

    np_acts-logits-general · gemini-2.0-flash

    economic concepts and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ญิง
    -0.66
    loit
    -0.65
    anskrit
    -0.63
    roek
    -0.61
     acyl
    -0.60
     Sede
    -0.59
     gardes
    -0.58
    vocable
    -0.57
    mobileqq
    -0.57
    otheby
    -0.56
    POSITIVE LOGITS
     economy
    0.96
    ECONOMIC
    0.94
     economies
    0.94
     economic
    0.89
     Economics
    0.88
     Economy
    0.88
    economic
    0.87
    wirtschaft
    0.87
     Economic
    0.86
    econom
    0.86
    Activations Density 0.062%

    No Known Activations