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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109618
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "first" and related terms indicating primacy or originality

    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
     arşivlendi
    -0.49
    ///</
    -0.37
     militaires
    -0.35
     Lokales
    -0.35
    nonatomic
    -0.35
     tidigare
    -0.35
     kvinder
    -0.34
    ImageContext
    -0.34
     înainte
    -0.34
     cref
    -0.34
    POSITIVE LOGITS
    uxxxx
    0.51
    
    0.51
    第一次
    0.50
     NSCoder
    0.47
     Venezia
    0.47
    pompa
    0.46
     utafitiHapana
    0.46
     Fah
    0.45
    TOM
    0.45
    PARATUS
    0.45
    Activations Density 0.140%

    No Known Activations