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

    Neuronpedia

    Jacobian LensNEW
    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. 109418
    Prev
    Next
    INDEX
    Explanations

    references to lap times and positions in a race context

    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
     lap
    -1.51
     laps
    -1.16
    lap
    -1.04
     Lap
    -1.02
    Lap
    -0.98
    LAP
    -0.81
    laps
    -0.77
     LAP
    -0.74
    ラップ
    -0.52
     bezeichneter
    -0.48
    POSITIVE LOGITS
    enterOuterAlt
    0.38
     bén
    0.37
     osobow
    0.34
    usercontent
    0.33
    SequentialGroup
    0.33
    IBOutlet
    0.33
    binaan
    0.33
    usermodel
    0.31
     Thun
    0.31
     podjela
    0.31
    Activations Density 0.002%

    No Known Activations