© 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. 24-GEMMASCOPE-RES-16K
    11. 1812
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "early" in various contexts

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

    "early" followed by a unit of time

    np_acts-logits-general · gemini-2.0-flash

    early time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wicidata
    -0.68
     pozdě
    -0.66
     senere
    -0.65
     earlier
    -0.64
     bientôt
    -0.64
     tidligere
    -0.64
     tidigare
    -0.61
     Earlier
    -0.60
     sooner
    -0.60
    Later
    -0.60
    POSITIVE LOGITS
     adopter
    0.91
     adop
    0.89
     morning
    0.88
     stages
    0.85
    bird
    0.78
    TagMode
    0.75
     EconPapers
    0.75
    morning
    0.75
     bird
    0.73
     days
    0.72
    Activations Density 0.071%

    No Known Activations