© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4391
    Prev
    Next
    INDEX
    Explanations

    time-related expressions and mentions of past experiences

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

    "For" followed by a time period

    np_acts-logits-general · gemini-2.0-flash

    duration of time

    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
     başına
    -0.53
     habet
    -0.45
    äiv
    -0.44
     برانيه
    -0.42
     Geen
    -0.42
    óngase
    -0.41
    lars
    -0.40
     спустя
    -0.40
    olfo
    -0.38
    tetés
    -0.38
    POSITIVE LOGITS
     quite
    1.10
     years
    1.06
     awhile
    1.02
     ages
    0.99
    complexContent
    0.99
    quite
    0.96
     Quite
    0.96
     long
    0.93
     longtemps
    0.92
    Quite
    0.91
    Activations Density 0.124%

    No Known Activations