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

    Neuronpedia

    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. 31-GEMMASCOPE-RES-131K
    11. 20929
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating conditional or situational context

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

    while or incidentally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.40
    uttavia
    -0.40
    mobileqq
    -0.39
    artiges
    -0.39
     медленно
    -0.38
     lắm
    -0.37
    epam
    -0.37
     constantly
    -0.37
    ricted
    -0.37
     pymongo
    -0.37
    POSITIVE LOGITS
    ついでに
    1.36
     while
    1.15
    while
    1.13
    顺便
    1.05
    ついで
    1.05
     mientras
    1.00
    WHILE
    0.95
     WHILE
    0.95
    While
    0.94
     Aprove
    0.93
    Activations Density 0.042%

    No Known Activations