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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 109465
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of decay in various contexts

    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
     decay
    -2.05
     Decay
    -1.82
    decay
    -1.74
    Decay
    -1.67
     decays
    -1.53
     decayed
    -1.32
     decaying
    -1.21
    deca
    -0.85
    衰
    -0.75
     deca
    -0.73
    POSITIVE LOGITS
    zijde
    0.43
     kří
    0.41
     casquette
    0.40
     pov
    0.39
     vyst
    0.38
     piatta
    0.38
     vueltas
    0.38
    zwi
    0.37
     unofficial
    0.37
    ținut
    0.36
    Activations Density 0.004%

    No Known Activations