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. 90016
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references associated with contracts

    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
    -0.67
     للاسماء
    -0.66
     pinulongan
    -0.66
     AssemblyCulture
    -0.65
    IsMutable
    -0.60
    tanleria
    -0.59
    IUrlHelper
    -0.59
    Билгалдахарш
    -0.56
    tvguidetime
    -0.55
    évaluateur
    -0.54
    POSITIVE LOGITS
     prior
    0.41
    alarm
    0.41
     prospec
    0.41
     Bav
    0.40
     line
    0.40
     plan
    0.40
     planning
    0.39
     صف
    0.39
     Bab
    0.39
     pre
    0.38
    Activations Density 0.142%

    No Known Activations