© 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. 16-GEMMASCOPE-RES-16K
    11. 10603
    Prev
    Next
    INDEX
    Explanations

    phrases or idioms that suggest comfort or solutions to problems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Text after quotation marks or punctuation

    np_acts-logits-general · gemini-2.0-flash

    code and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    vable
    -0.43
     scores
    -0.42
    といって
    -0.41
    oly
    -0.40
    டுக
    -0.40
    HttpFoundation
    -0.40
    AfterClass
    -0.40
    isible
    -0.39
     dot
    -0.39
    DeleteBehavior
    -0.39
    POSITIVE LOGITS
     viewDidLoad
    0.83
    tagHelperRunner
    0.78
    ///</
    0.73
    __':
    0.69
     useStyles
    0.67
     >=",
    0.66
    TextAppearance
    0.64
     doGet
    0.64
    CppMethod
    0.62
    LEncoder
    0.62
    Activations Density 0.195%

    No Known Activations