© 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. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103672
    Prev
    Next
    INDEX
    Explanations

    references to seasons in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.74
    niſſe
    -0.70
    ConstraintMaker
    -0.69
     utafitiHapana
    -0.67
     Geſch
    -0.67
     Weiſe
    -0.67
     propOrder
    -0.65
    GEBURTSDATUM
    -0.65
    ⟬
    -0.65
    ஦
    -0.65
    POSITIVE LOGITS
     surla
    0.43
     season
    0.43
     played
    0.38
     performance
    0.35
     NgModule
    0.35
     results
    0.34
     Coach
    0.33
     following
    0.32
     playing
    0.31
     proved
    0.31
    Activations Density 0.015%

    No Known Activations