Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 131040
    Prev
    Next
    INDEX
    Explanations

    references to social groups and political coalitions

    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
     alberi
    -0.35
     adaptée
    -0.32
    mRecyclerView
    -0.28
     commandés
    -0.27
     paid
    -0.27
     wpis
    -0.27
    ंत
    -0.27
     Parrot
    -0.26
     ponte
    -0.26
    lstm
    -0.26
    POSITIVE LOGITS
    :✨
    0.75
    httphttps
    0.66
     alliance
    0.66
     alliances
    0.65
    SequentialGroup
    0.64
    ChildScrollView
    0.63
    alliance
    0.63
    ⓧ
    0.61
     assemb
    0.60
     groupings
    0.60
    Activations Density 0.157%

    No Known Activations