© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 701
    Prev
    Next
    INDEX
    Explanations

    the word "which" in various contexts

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

    which followed by pronoun or noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reathable
    -0.55
    odyear
    -0.53
     Gunter
    -0.48
    Keller
    -0.48
     Leno
    -0.47
    btnBack
    -0.47
     Munster
    -0.47
    ditor
    -0.47
     createDate
    -0.47
    psd
    -0.46
    POSITIVE LOGITS
    which
    0.65
     WHICH
    0.65
    Which
    0.60
     Which
    0.57
     duquel
    0.55
     wich
    0.53
     which
    0.52
    hich
    0.52
     whereof
    0.51
    whom
    0.51
    Activations Density 0.037%

    No Known Activations