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. 62291
    Prev
    Next
    INDEX
    Explanations

    negative aspects or limitations of a product or service

    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
    ValueStyle
    -0.37
    verticalLayout
    -0.33
     StatefulWidget
    -0.31
     belief
    -0.30
     continued
    -0.29
    pretation
    -0.29
    //*[@
    -0.29
    Sl
    -0.29
     lasting
    -0.28
    styleUrls
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.67
     CreateTagHelper
    0.60
    featureID
    0.58
     ujednoznacz
    0.57
     inconvenient
    0.57
    不便
    0.54
     externi
    0.53
    Conclusie
    0.53
     Insufficient
    0.52
    Билгалдахарш
    0.52
    Activations Density 0.033%

    No Known Activations