© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 3311
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to competition and performance in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.96
     المعيارى
    -0.80
     <=",
    -0.75
     kasarigan
    -0.70
    sizeCache
    -0.70
     تانيه
    -0.69
    endcsname
    -0.66
     pinulongan
    -0.66
    Билгалдахарш
    -0.65
    DispatchToProps
    -0.64
    POSITIVE LOGITS
     Runners
    0.57
     Marathon
    0.54
     marathon
    0.52
     runners
    0.51
    Marathon
    0.50
     triathlon
    0.47
     marat
    0.47
    MIDDLEWARE
    0.46
     Runner
    0.44
    oznam
    0.44
    Activations Density 0.104%

    No Known Activations