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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117394
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables associated with equations and formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     autorytatywna
    -0.69
    Autoritní
    -0.69
    providedIn
    -0.68
     betweenstory
    -0.60
    abestanden
    -0.57
     Chwiliwch
    -0.57
     otomatig
    -0.55
    
    -0.55
    sizeCache
    -0.55
    UserScript
    -0.54
    POSITIVE LOGITS
     fieldNum
    0.41
    tų
    0.33
    обще
    0.30
    >::
    0.28
    }>;
    0.27
    ):(
    0.26
     sigu
    0.26
    ["
    0.26
    ","","
    0.26
    eseorang
    0.25
    Activations Density 0.292%

    No Known Activations