© 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. 13136
    Prev
    Next
    INDEX
    Explanations

    contexts referring to time, particularly in relation to events occurring "before" or "prior to" a specified point

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

    before or prior to

    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
     आइटम
    -0.28
    makaian
    -0.28
    Rund
    -0.27
    tracker
    -0.26
     coordinate
    -0.25
    tku
    -0.25
     ἄ
    -0.25
    cast
    -0.24
    ◎
    -0.24
    Flags
    -0.23
    POSITIVE LOGITS
     before
    1.11
     sebelum
    1.02
     ennen
    1.00
    before
    0.98
     antes
    0.97
     Before
    0.94
    Before
    0.93
     BEFORE
    0.91
    BEFORE
    0.90
     bevor
    0.89
    Activations Density 0.055%

    No Known Activations