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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 7365
    Prev
    Next
    INDEX
    Explanations

    dates and significant events associated with seasonal transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     summer
    -0.90
     Summer
    -0.88
    Summer
    -0.87
     summers
    -0.84
    summer
    -0.84
    June
    -0.84
     June
    -0.83
     SUMMER
    -0.80
    SUMMER
    -0.78
     JUNE
    -0.75
    POSITIVE LOGITS
     November
    1.62
    November
    1.55
     October
    1.50
    NOVEMBER
    1.48
     Nov
    1.45
     NOVEMBER
    1.44
    October
    1.43
    Thanksgiving
    1.39
     Thanksgiving
    1.38
     Halloween
    1.37
    Activations Density 0.217%

    No Known Activations