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. 22-GEMMASCOPE-RES-16K
    6. 7994
    Prev
    Next
    INDEX
    Explanations

    references to the New Year celebrations and related cultural practices

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

    the new year

    np_acts-logits-general · gemini-2.0-flash

    new year resolutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.62
    Autoritní
    -0.58
    ContentAsync
    -0.55
     المعيارى
    -0.55
     butterknife
    -0.55
     Italijani
    -0.50
    ritsar
    -0.48
     насељу
    -0.48
     Helio
    -0.47
    icznej
    -0.47
    POSITIVE LOGITS
     New
    1.80
    New
    1.54
     resolutions
    1.38
     resolution
    1.25
     Resolution
    1.20
     Resolutions
    1.19
    Resolution
    1.08
     NY
    1.08
    resolution
    1.05
     NEW
    1.05
    Activations Density 0.137%

    No Known Activations