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. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109754
    Prev
    Next
    INDEX
    Explanations

    topics related to controversies and public outrage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.69
     ویکی‌پدیا
    -0.64
    delwed
    -0.63
     HasFactory
    -0.62
     FetchType
    -0.60
     esternos
    -0.58
     ModelExpression
    -0.57
    
    -0.57
    SBATCH
    -0.56
    🔕
    -0.56
    POSITIVE LOGITS
     honneur
    0.38
     amitié
    0.34
    richTextPanel
    0.32
     warunki
    0.31
     Faktoren
    0.30
     toit
    0.29
    torie
    0.29
     Imperio
    0.29
     Pflichten
    0.28
     vergleich
    0.28
    Activations Density 0.016%

    No Known Activations