© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1361
    Prev
    Next
    INDEX
    Explanations

    terms associated with medical conditions or health-related discussions

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

    ending in "ly"

    np_acts-logits-general · gemini-2.0-flash

    adverbs and specific technical terms

    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
     AssemblyCulture
    -0.70
    发表于
    -0.66
    AYO
    -0.66
    IsContent
    -0.64
     Baillargeon
    -0.64
     hangat
    -0.63
    glGen
    -0.63
    帖最后由
    -0.62
    :+:
    -0.62
    
    -0.62
    POSITIVE LOGITS
    ly
    0.66
    までに
    0.60
     vérité
    0.53
    erweise
    0.52
    ほどの
    0.52
     levels
    0.52
    ingly
    0.51
     speed
    0.51
     grin
    0.49
     prolifer
    0.49
    Activations Density 0.240%

    No Known Activations