© 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. 3307
    Prev
    Next
    INDEX
    Explanations

    date-related expressions

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

    Days of the week

    np_acts-logits-general · gemini-2.0-flash

    days of the week and times

    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
    +#+#
    -0.69
    存于互联网档案馆
    -0.57
    pexpr
    -0.54
    ]--;
    -0.49
    pec
    -0.48
    AndroidJUnit
    -0.48
    ibatis
    -0.48
    MetaType
    -0.45
     cas
    -0.44
    orius
    -0.44
    POSITIVE LOGITS
     morning
    1.31
     afternoon
    1.29
     evening
    1.25
     night
    1.24
     mornings
    1.18
     afternoons
    1.15
    evening
    1.07
    morning
    1.06
     evenings
    1.05
     nights
    1.02
    Activations Density 0.069%

    No Known Activations