© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1343
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize making decisions or taking action at specific times

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

    phrases or concepts related to change and new beginnings

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

    time to act

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    fjspx
    -0.63
    Затем
    -0.62
    TagHelper
    -0.61
    posedge
    -0.61
     następnie
    -0.60
     later
    -0.60
    later
    -0.60
    ouille
    -0.59
     successively
    -0.59
     nanti
    -0.59
    POSITIVE LOGITS
     reconsider
    0.78
     revisit
    0.73
     rethink
    0.70
     seriously
    0.68
     start
    0.67
     reass
    0.67
     serious
    0.66
     stop
    0.64
     freshen
    0.62
    seriously
    0.61
    Activations Density 0.096%

    No Known Activations