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

    Neuronpedia

    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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 294
    Prev
    Next
    INDEX
    Explanations

    significant moments or scoring events in sports narratives

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

    scores, ranges, or results

    np_acts-logits-general · gemini-2.0-flash

    sports results and scores

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    tagHelperRunner
    -0.79
    ंदीखरीदारी
    -0.76
     pinulongan
    -0.62
    ➯
    -0.56
    ientras
    -0.52
     murni
    -0.52
    
    -0.52
     Theſe
    -0.49
    ⤹
    -0.48
     trasparente
    -0.48
    POSITIVE LOGITS
     pulled
    0.43
     kick
    0.42
    kick
    0.40
     struck
    0.39
    cris
    0.38
     grabbed
    0.38
     kicked
    0.37
    GEBURTSDATUM
    0.37
    Hentet
    0.37
     createSlice
    0.36
    Activations Density 0.052%

    No Known Activations