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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53408
    Prev
    Next
    INDEX
    Explanations

    references to time and seasonal events

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

    April and spring months

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    NOVEMBER
    -0.74
     Thanksgiving
    -0.71
     christmas
    -0.71
     Nov
    -0.71
     Pumpkin
    -0.69
    Thanksgiving
    -0.69
    christmas
    -0.69
     NOVEMBER
    -0.68
     Christmas
    -0.67
    🎃
    -0.67
    POSITIVE LOGITS
     April
    1.05
    April
    0.99
     spring
    0.98
     March
    0.97
    March
    0.93
     Spring
    0.93
    Spring
    0.93
     springtime
    0.92
    APRIL
    0.88
     Easter
    0.87
    Activations Density 0.082%

    No Known Activations