© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 16129
    Prev
    Next
    INDEX
    Explanations

    information related to injury status and player updates in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.80
     TextInputType
    -0.71
    CloseOperation
    -0.67
    Xna
    -0.62
     scholastic
    -0.61
     undefeated
    -0.61
     idéia
    -0.60
    riterion
    -0.60
    Coach
    -0.59
    wpi
    -0.59
    POSITIVE LOGITS
    捗
    0.57
    pantalones
    0.50
     LEYENDO
    0.49
     massive
    0.48
     $"{
    0.48
    Derp
    0.47
    nop
    0.47
    itest
    0.47
    riol
    0.47
     regression
    0.46
    Activations Density 0.218%

    No Known Activations