© 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. 15-GEMMASCOPE-RES-16K
    11. 3898
    Prev
    Next
    INDEX
    Explanations

    references to time and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bibliograf
    -0.71
    Autoritní
    -0.70
     fers
    -0.64
     bezeichneter
    -0.62
     compr
    -0.61
    теристика
    -0.61
     protoimpl
    -0.58
    Enllaces
    -0.57
     McDonough
    -0.56
     Scherer
    -0.56
    POSITIVE LOGITS
     time
    1.44
     Time
    1.21
     TIME
    1.21
    time
    1.20
     getTime
    1.13
     setTime
    1.10
    TIME
    1.09
    getTime
    1.07
    Time
    1.01
     times
    0.98
    Activations Density 0.171%

    No Known Activations