© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 40828
    Prev
    Next
    INDEX
    Explanations

    instances of the word "a" and phrases that emphasize quantity or specificity

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

    just a minor instance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Budaya
    -0.56
     Usaha
    -0.55
     Utama
    -0.54
     Putih
    -0.53
     Komunikasi
    -0.51
     Bisnis
    -0.50
     Kebijakan
    -0.50
     Pembangunan
    -0.48
     Hidup
    -0.48
     Lainnya
    -0.47
    POSITIVE LOGITS
     mere
    0.63
     مجرد
    0.62
    ただの
    0.59
     MainAxisSize
    0.54
    Mere
    0.54
    只是一
    0.53
     insignificant
    0.53
    mere
    0.52
     blink
    0.51
     shrugged
    0.50
    Activations Density 0.026%

    No Known Activations