© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 67033
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or entities named "Da" or variations of that name

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

    Da followed by vinc, ika,ubin

    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
    Connell
    -0.63
     Económica
    -0.61
     pierna
    -0.56
     inversión
    -0.52
     educativos
    -0.51
     rodilla
    -0.50
     incertidumbre
    -0.50
    berdayakan
    -0.49
     כול
    -0.49
     Políticas
    -0.49
    POSITIVE LOGITS
     Da
    0.91
     da
    0.82
     DA
    0.81
     Dahl
    0.81
    Da
    0.80
    da
    0.71
    DA
    0.68
     Daf
    0.67
     Dal
    0.65
     D
    0.64
    Activations Density 0.011%

    No Known Activations