© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109230
    Prev
    Next
    INDEX
    Explanations

    specific programming-related constructs and terms

    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
    parsedMessage
    -0.88
    StoryboardSegue
    -0.80
     enfans
    -0.76
     pleaſure
    -0.74
     Chriftian
    -0.74
     fubject
    -0.72
     Jefus
    -0.72
     Reſ
    -0.71
     purpoſe
    -0.71
     ſche
    -0.71
    POSITIVE LOGITS
     communiquer
    0.28
    tences
    0.25
     ребен
    0.25
     solucionar
    0.23
    ―
    0.23
     Stunden
    0.23
     Kommunikation
    0.22
     conjunta
    0.22
     Konkurrenz
    0.22
     mergul
    0.21
    Activations Density 0.051%

    No Known Activations