© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 474
    Prev
    Next
    INDEX
    Explanations

    sports statistics and player performance metrics

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

    occurrences of numerical data and their contexts, particularly regarding sports statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.65
     resourceCulture
    -0.65
     @"/
    -0.57
    contentLoaded
    -0.53
    ագրություններ
    -0.51
    Bounding
    -0.46
    fromUtf
    -0.45
     ISNI
    -0.45
    ikke
    -0.45
     Bloomsbury
    -0.44
    POSITIVE LOGITS
    AutoresizingMask
    0.61
    ódó
    0.54
     <>",
    0.53
    "';
    0.53
    KommentareTeilen
    0.52
    preduce
    0.52
    jší
    0.50
    modb
    0.50
     StatefulWidget
    0.50
     pendulum
    0.50
    Activations Density 0.235%

    No Known Activations