© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35282
    Prev
    Next
    INDEX
    Explanations

    references to specific publications or journals

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

    detecting French "du" and words starting with "Du"

    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
     Económica
    -0.57
     ainfi
    -0.54
     inoxydable
    -0.53
     nôtre
    -0.53
     oeil
    -0.52
     incendie
    -0.51
     enfans
    -0.50
     infierno
    -0.50
     Arbeitnehmer
    -0.50
     bénévol
    -0.48
    POSITIVE LOGITS
     Du
    1.20
     DU
    1.13
     du
    1.07
    Du
    1.05
     Duval
    0.98
     Duch
    0.85
     DUP
    0.84
     Duf
    0.83
    du
    0.81
     duvet
    0.80
    Activations Density 0.013%

    No Known Activations