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. 62297
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people and places

    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
    s
    -0.47
     bArr
    -0.47
     NSCoder
    -0.43
     Maths
    -0.41
     labourer
    -0.40
    Maths
    -0.39
    UAV
    -0.38
     PLoS
    -0.37
    手
    -0.37
     labourers
    -0.37
    POSITIVE LOGITS
     للاسماء
    0.90
     فريبيس
    0.77
     للمعارف
    0.75
    gerald
    0.72
    ValueStyle
    0.71
    حياته
    0.68
    niſſe
    0.68
    linawan
    0.68
    ſicht
    0.68
    czaj
    0.67
    Activations Density 0.025%

    No Known Activations