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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 1059
    Prev
    Next
    INDEX
    Explanations

    phrases that signal contrast or opposition within sentences

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

    but and continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    
    -0.63
    出版年
    -0.61
     BoxDecoration
    -0.58
    ArgumentParser
    -0.52
    存于互联网档案馆
    -0.52
     NgModule
    -0.51
     disponibilités
    -0.51
    новниш
    -0.50
    itemBuilder
    -0.49
    مصادر
    -0.49
    POSITIVE LOGITS
    Tikang
    0.36
     Administrativna
    0.35
     vriende
    0.34
     BoxFit
    0.34
     nothing
    0.33
     siedz
    0.33
     zijne
    0.33
    nothing
    0.32
     otherwise
    0.32
     lendemain
    0.31
    Activations Density 0.054%

    No Known Activations