© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15263
    Prev
    Next
    INDEX
    Explanations

    phrases that denote specific times of the day, particularly related to morning

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

    the time "morning"

    np_acts-logits-general · gemini-2.0-flash

    morning and breakfast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.88
    IsContent
    -0.77
    bootstrapcdn
    -0.74
    ########.
    -0.73
    ⓧ
    -0.70
     pinulongan
    -0.70
    TagMode
    -0.70
    Autoritní
    -0.69
     esternos
    -0.66
    Pyx
    -0.65
    POSITIVE LOGITS
     morning
    1.22
     Morning
    1.20
     breakfast
    1.10
     Breakfast
    1.10
    Morning
    1.09
     mornings
    1.08
     MORNING
    1.07
    morning
    1.03
    Breakfast
    1.03
     breakfasts
    1.00
    Activations Density 0.075%

    No Known Activations