© 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. 10342
    Prev
    Next
    INDEX
    Explanations

    instances of the word "now" in various forms and contexts

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

    "now"

    np_acts-logits-general · gemini-2.0-flash

    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
     Sabo
    -0.61
     APE
    -0.58
    iParam
    -0.56
    vari
    -0.55
     professionali
    -0.55
    UIControlState
    -0.54
    ების
    -0.54
    로운
    -0.53
    ροι
    -0.53
    SqlClient
    -0.53
    POSITIVE LOGITS
    adays
    0.97
    HERE
    0.84
    wwwwwwww
    0.82
     صوتيه
    0.76
    værende
    0.74
    WWWW
    0.73
    wwww
    0.73
     Mow
    0.73
     NOW
    0.73
    ValueStyle
    0.72
    Activations Density 0.087%

    No Known Activations