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. 383
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal and regulatory contexts

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

    technical terms and specific quantities or measurements, often related to engineering, legal, or scientific contexts.

    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
    printStackTrace
    -0.54
    rench
    -0.52
     Signalez
    -0.50
    urma
    -0.48
    ناعة
    -0.47
    enite
    -0.47
     Conroy
    -0.46
    *}[
    -0.45
    Slik
    -0.45
    IContainer
    -0.45
    POSITIVE LOGITS
     resourceCulture
    0.83
    Small
    0.76
    astéroïdes
    0.76
     Small
    0.71
    Smaller
    0.69
     small
    0.69
     smaller
    0.68
     Kecil
    0.67
     Everyday
    0.66
     ارزان
    0.66
    Activations Density 1.021%

    No Known Activations