© 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. 4103
    Prev
    Next
    INDEX
    Explanations

    instances of the word "you" and its variations to gauge direct engagement or inquiry

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

    you followed by a verb in a question

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

    the neuron detects interrogative sentence openers—especially question phrases like "Do/Did/Are/How/What" often addressing "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
     rhestr
    -0.57
    ⤒
    -0.52
    ]")]
    -0.50
     kaynağından
    -0.47
    EndContext
    -0.46
    adaptiveStyles
    -0.45
    +#+#
    -0.45
    Tembelea
    -0.45
     setObject
    -0.44
     BoxFit
    -0.43
    POSITIVE LOGITS
    featureID
    0.45
    fromnode
    0.39
    ガニック
    0.36
     confidence
    0.33
     ulang
    0.32
     answer
    0.32
    retra
    0.32
     humano
    0.32
    Oso
    0.32
    押
    0.32
    Activations Density 0.020%

    No Known Activations