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. 13-GEMMASCOPE-RES-16K
    6. 63
    Prev
    Next
    INDEX
    Explanations

    references to large numerical values, especially in the context of billions and millions

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

    large monetary values, specifically in billions.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.86
    شوند
    -0.66
    geschenk
    -0.61
    elett
    -0.61
     Orrell
    -0.61
    shoe
    -0.60
    ILayout
    -0.56
    rouw
    -0.55
     douleurs
    -0.54
    shoes
    -0.54
    POSITIVE LOGITS
     billion
    1.49
     billions
    1.26
     million
    1.25
     Billion
    1.25
    billion
    1.21
     trillion
    1.16
    Millions
    1.16
     milliard
    1.10
     milliards
    1.10
     millones
    1.08
    Activations Density 0.083%

    No Known Activations