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. 109530
    Prev
    Next
    INDEX
    Explanations

    terms related to postponement and delays

    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
     postpone
    -1.43
     postponed
    -1.40
     postpon
    -1.26
     postponement
    -1.23
     rescheduled
    -0.75
     reschedule
    -0.74
     delayed
    -0.65
     delaying
    -0.65
     delay
    -0.59
     deferred
    -0.58
    POSITIVE LOGITS
    BagConstraints
    0.59
     StatelessWidget
    0.56
     ExecuteAsync
    0.55
    ImageContext
    0.54
     Waray
    0.54
    RenderAtEndOf
    0.52
    ="@+
    0.52
     CreateTagHelper
    0.52
     mouseY
    0.49
    ppuden
    0.49
    Activations Density 0.003%

    No Known Activations