Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1623
    Prev
    Next
    INDEX
    Explanations

    references to seasonal periods, specifically summer

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

    "Summer" or "winter" season

    np_acts-logits-general · gemini-2.0-flash

    summer season context

    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
     InputDecoration
    -0.87
    IntoConstraints
    -0.79
    MessageTagHelper
    -0.74
    \]
    -0.73
    }\]
    -0.73
    Personensuche
    -0.72
     transfieras
    -0.71
    tvguidetime
    -0.71
     AssemblyCulture
    -0.70
     autorytatywna
    -0.67
    POSITIVE LOGITS
     Summer
    0.85
     season
    0.77
    y
    0.77
     summer
    0.75
    Summer
    0.75
     solstice
    0.74
     months
    0.70
     verano
    0.64
    SUMMER
    0.62
     seasons
    0.62
    Activations Density 0.071%

    No Known Activations