© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10400
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until" and related temporal phrases

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

    Followed by "the", "now", or "recently"

    np_acts-logits-general · gemini-2.0-flash

    until now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    djangoproject
    -0.82
     Shakspeare
    -0.82
     RSSSF
    -0.75
    IBOutlet
    -0.75
     Florentine
    -0.74
     Majefty
    -0.73
     habet
    -0.72
    makeText
    -0.71
     Jpn
    -0.70
     Navajo
    -0.69
    POSITIVE LOGITS
     until
    1.20
     till
    1.06
     UNTIL
    1.04
     til
    1.03
    until
    1.02
     Until
    1.00
     untill
    1.00
    Until
    0.99
     Til
    0.92
    Til
    0.90
    Activations Density 0.056%

    No Known Activations