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. 22365
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts related to problems caused by industrial actions and their effects on various entities

    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
     kasarigan
    -0.73
     Exacts
    -0.58
    Бахар
    -0.50
    verwijspagina
    -0.50
     للاسماء
    -0.49
    Rhestr
    -0.49
     wireType
    -0.49
    AddHtmlAttribute
    -0.48
    matchCondition
    -0.47
    astify
    -0.47
    POSITIVE LOGITS
     držav
    0.40
    ances
    0.38
     cuestión
    0.37
     questão
    0.34
     поза
    0.33
    dependencies
    0.32
     préstamo
    0.32
    führende
    0.31
    urou
    0.31
     localObject
    0.31
    Activations Density 0.198%

    No Known Activations