© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7767
    Prev
    Next
    INDEX
    Explanations

    instances of time-related phrases or events

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

    Following "Last" plus a unit of time

    np_acts-logits-general · gemini-2.0-flash

    last + time indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.60
     eventdata
    -0.60
     manhã
    -0.57
    TintMode
    -0.57
     pozdě
    -0.56
    PyExc
    -0.56
     позже
    -0.55
     defaultstate
    -0.54
    VideoCapture
    -0.54
     splet
    -0.53
    POSITIVE LOGITS
     minute
    0.91
     resort
    0.90
    minute
    0.83
    ingly
    0.78
    PerformLayout
    0.78
    est
    0.77
    resort
    0.77
     few
    0.75
     Resort
    0.74
     straw
    0.73
    Activations Density 0.080%

    No Known Activations