© 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. 10571
    Prev
    Next
    INDEX
    Explanations

    instances of time-related language, emphasizing later and earlier occurrences

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

    "later"

    np_acts-logits-general · gemini-2.0-flash

    later

    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
    parsedMessage
    -0.66
    исленность
    -0.60
     المعيارى
    -0.52
     esternos
    -0.52
    formerly
    -0.52
     sebelumnya
    -0.52
     ​​
    -0.51
     tenuta
    -0.51
     &___
    -0.50
     précédentes
    -0.50
    POSITIVE LOGITS
     generations
    0.89
     than
    0.87
     дописавши
    0.75
     stages
    0.73
    enumi
    0.72
     editions
    0.71
    CloseOperation
    0.70
    ⓧ
    0.70
    itic
    0.69
     versions
    0.68
    Activations Density 0.087%

    No Known Activations