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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4217
    Prev
    Next
    INDEX
    Explanations

    references to news articles and publications

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

    "The" preceding news outlets

    np_acts-logits-general · gemini-2.0-flash

    names of newspapers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.80
    SharedDtor
    -0.78
    ChildIndex
    -0.78
     Италијани
    -0.70
    writeFieldEnd
    -0.69
    出版年
    -0.68
    ☸
    -0.65
     AssemblyCulture
    -0.64
     linkovi
    -0.62
    HtmlAttribute
    -0.61
    POSITIVE LOGITS
     Times
    1.00
     NYT
    0.97
     Associated
    0.91
    nytimes
    0.88
     Reuters
    0.84
     Guardian
    0.81
    Times
    0.77
     BBC
    0.77
    Associated
    0.75
     Washington
    0.75
    Activations Density 0.213%

    No Known Activations