© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35558
    Prev
    Next
    INDEX
    Explanations

    terms related to fouls and negative actions in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    foul and related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.68
     indígen
    -0.63
    DotNetBar
    -0.59
     Autorizaciones
    -0.59
    Personendaten
    -0.58
     Autorisations
    -0.57
    <unused28>
    -0.57
    <pad>
    -0.57
     purpoſe
    -0.57
    <unused8>
    -0.57
    POSITIVE LOGITS
     foul
    1.95
     Foul
    1.83
    foul
    1.79
     fouls
    1.41
     fouling
    1.24
     fou
    1.14
     Fou
    1.06
    Fou
    1.01
    fou
    0.99
     fowl
    0.79
    Activations Density 0.002%

    No Known Activations