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. 25-GEMMASCOPE-RES-16K
    6. 5755
    Prev
    Next
    INDEX
    Explanations

    names of individuals and references to authors

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

    bibliographic citation details and academic reference formatting elements

    oai_token-act-pair · o3-miniTriggered by @yemengyus1
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Support
    -0.35
     Background
    -0.35
     Experience
    -0.34
     Practice
    -0.33
     Online
    -0.33
     Complete
    -0.32
     Features
    -0.32
     Information
    -0.32
     Training
    -0.32
     Working
    -0.32
    POSITIVE LOGITS
     Pizarro
    0.36
     autorytatywna
    0.35
     Krueger
    0.35
     Pfeiffer
    0.33
     Romero
    0.33
     Sandberg
    0.33
     Nicholson
    0.33
     Orozco
    0.33
     Schweitzer
    0.33
     Zamora
    0.33
    Activations Density 29.903%

    No Known Activations