© 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. 66653
    Prev
    Next
    INDEX
    Explanations

    mentions of the pronoun "you"

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

    addressing the reader directly

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects direct second-person address—instances where the text addresses the reader (you).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    msgTypes
    -0.51
    TagMode
    -0.47
    rungsseite
    -0.44
     nahilalakip
    -0.42
     merawat
    -0.41
    Parcelize
    -0.40
    Aholisi
    -0.40
    脚注の使い方
    -0.39
    expandindo
    -0.39
     practices
    -0.37
    POSITIVE LOGITS
     AssemblyProduct
    0.55
     mirth
    0.50
     CanadaChoose
    0.47
     laugh
    0.46
     canine
    0.44
     Wikimedijinoj
    0.44
    dafx
    0.44
     Италијани
    0.44
     blitz
    0.44
     giggle
    0.43
    Activations Density 0.001%

    No Known Activations