© 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. 73222
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "which."

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

    which + noun followed by a question

    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
    CDA
    -0.42
    abstra
    -0.41
     geboten
    -0.41
    NST
    -0.39
    dura
    -0.39
    про
    -0.39
    au
    -0.39
    FIS
    -0.38
    tn
    -0.38
    fD
    -0.38
    POSITIVE LOGITS
     Which
    0.96
     WHICH
    0.94
    Which
    0.94
     wich
    0.74
    Wich
    0.73
    Welke
    0.69
     Wich
    0.69
    which
    0.67
     which
    0.67
    hich
    0.64
    Activations Density 0.038%

    No Known Activations