© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 60259
    Prev
    Next
    INDEX
    Explanations

    references to sports matches and match days

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

    match day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    omitempty
    -0.70
    orio
    -0.63
    tori
    -0.63
     nahilalakip
    -0.61
     Савезне
    -0.61
    onik
    -0.59
    tubers
    -0.58
    erstein
    -0.58
     Sinai
    -0.58
    Portale
    -0.58
    POSITIVE LOGITS
    match
    1.07
     match
    1.06
     Match
    1.05
    Match
    1.00
     MATCH
    0.91
    MATCH
    0.90
     matches
    0.77
     Matches
    0.71
    matches
    0.68
     matchs
    0.65
    Activations Density 0.014%

    No Known Activations