© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31817
    Prev
    Next
    INDEX
    Explanations

    instances of the word "define" and its variations, indicating a focus on defining concepts or objects

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    defining terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ฤษ
    -0.68
    KommentareTeilen
    -0.63
     Reproduce
    -0.56
    ynchro
    -0.56
     TRAB
    -0.55
    gjenge
    -0.54
     Lieu
    -0.54
    őben
    -0.52
    wantErr
    -0.52
    \!
    -0.52
    POSITIVE LOGITS
    aarrggbb
    1.00
    Defines
    0.97
     defines
    0.94
    defines
    0.94
     Defin
    0.94
     Defines
    0.93
     Defined
    0.93
     Define
    0.91
    define
    0.90
     define
    0.90
    Activations Density 0.069%

    No Known Activations