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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 93048
    Prev
    Next
    INDEX
    Explanations

    time-related numerical representations, particularly times and timestamps

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

    p.m. times

    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
    Lunch
    -0.65
    lunch
    -0.63
     Wicidata
    -0.61
     Lunch
    -0.59
     LUNCH
    -0.58
    SPATH
    -0.58
    seco
    -0.57
    OGND
    -0.56
    rungsseite
    -0.56
     lunch
    -0.56
    POSITIVE LOGITS
     night
    1.00
     Night
    0.89
     nights
    0.84
     nightly
    0.83
     tonight
    0.82
    night
    0.81
     NIGHT
    0.80
    Night
    0.78
     Nights
    0.74
    Tonight
    0.69
    Activations Density 0.024%

    No Known Activations