© 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. 18-GEMMASCOPE-RES-16K
    11. 6668
    Prev
    Next
    INDEX
    Explanations

    sexual references and explicit language

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

    Actions of falling, rolling, or lying

    np_acts-logits-general · gemini-2.0-flash

    lying, rolling, crawling

    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
    вол
    -0.56
    wand
    -0.51
    Wand
    -0.48
    wanda
    -0.47
    <eos>
    -0.47
     standard
    -0.45
    fontawesome
    -0.44
    挽
    -0.43
     Standard
    -0.43
    блу
    -0.42
    POSITIVE LOGITS
     crawling
    0.82
     lying
    0.78
     Lying
    0.75
     '\\;'
    0.75
     OFDb
    0.75
    Lying
    0.73
     crawl
    0.72
     crawled
    0.72
     crawls
    0.71
     groaning
    0.71
    Activations Density 0.166%

    No Known Activations