© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 11913
    Prev
    Next
    INDEX
    Explanations

    references to various seasons in a context, particularly in media, entertainment, or sports

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

    "season"

    np_acts-logits-general · gemini-2.0-flash

    season start, season end

    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
    IntoConstraints
    -0.90
     pinulongan
    -0.87
    %)$
    -0.79
    swire
    -0.77
     attent
    -0.75
    Salta
    -0.74
     resourceCulture
    -0.74
    ]));
    
    -0.73
    🏻‍♀️
    -0.70
    ibatis
    -0.69
    POSITIVE LOGITS
     season
    1.41
     seasons
    1.39
     Season
    1.26
    Seasons
    1.20
     Seasons
    1.19
     SEASON
    1.18
    Season
    1.16
    season
    1.16
    ASONS
    1.06
     saisons
    1.03
    Activations Density 0.060%

    No Known Activations