© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5375
    Prev
    Next
    INDEX
    Explanations

    references to dates and timelines in the text

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

    Dates, especially months

    np_acts-logits-general · gemini-2.0-flash

    calendar dates and months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.93
    expandindo
    -0.81
    CppMethod
    -0.76
    MLLoader
    -0.74
    TintMode
    -0.70
    gameserver
    -0.70
     utafitiHapana
    -0.69
    PerformLayout
    -0.68
    Сюжет
    -0.67
     متعلقه
    -0.67
    POSITIVE LOGITS
     January
    0.68
    January
    0.55
     Jan
    0.52
     July
    0.50
    JANUARY
    0.44
    january
    0.44
     first
    0.43
    ApiModelProperty
    0.43
     JANUARY
    0.42
     january
    0.42
    Activations Density 0.234%

    No Known Activations