© 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. 20-GEMMASCOPE-RES-131K
    11. 99491
    Prev
    Next
    INDEX
    Explanations

    instances of the word "before."

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

    temporal conjunctions

    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
    =$?
    -0.46
     accountId
    -0.43
    accountId
    -0.40
     Osun
    -0.40
    MLElement
    -0.40
    OECD
    -0.39
     Gedicht
    -0.38
     culturelles
    -0.38
     ilha
    -0.37
     Tatsache
    -0.37
    POSITIVE LOGITS
    before
    1.31
     before
    1.30
     BEFORE
    1.14
    Before
    1.14
     Before
    1.13
    BEFORE
    1.13
     sebelum
    0.94
    efore
    0.92
     før
    0.88
     antes
    0.88
    Activations Density 0.041%

    No Known Activations