© 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. 20-GEMMASCOPE-RES-16K
    11. 13074
    Prev
    Next
    INDEX
    Explanations

    temporal references related to events or actions over time

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

    following "since" or "before"

    np_acts-logits-general · gemini-2.0-flash

    time since event began

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     amanhã
    -0.72
     myö
    -0.68
     next
    -0.62
     ujednoznacz
    -0.61
     prochain
    -0.59
     upcoming
    -0.59
     demain
    -0.56
     tomorrow
    -0.55
     future
    -0.55
    verwijspagina
    -0.55
    POSITIVE LOGITS
     inception
    1.05
     began
    0.86
     Began
    0.79
     angefangen
    0.77
     började
    0.74
    StructEnd
    0.74
     started
    0.73
     llegada
    0.72
     onset
    0.71
     debuted
    0.70
    Activations Density 0.321%

    No Known Activations