© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4535
    Prev
    Next
    INDEX
    Explanations

    terms related to sports performance and player statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.56
    Ử
    -0.52
     zich
    -0.51
    beginTransaction
    -0.51
    ligente
    -0.50
     reprezenta
    -0.50
    tale
    -0.50
     faithful
    -0.49
     Hentet
    -0.49
     Freundschaft
    -0.48
    POSITIVE LOGITS
     pinulongan
    0.70
    MigrationBuilder
    0.70
    Tikang
    0.63
    DockStyle
    0.62
     autorytatywna
    0.61
    +#+
    0.58
    cloudflare
    0.57
     nahilalakip
    0.56
     ligiloj
    0.56
    клопе
    0.56
    Activations Density 0.211%

    No Known Activations