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

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 6222
    Prev
    Next
    INDEX
    Explanations

    specific start-of-sequence tokens in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nestjs
    -0.92
    SourceChecksum
    -0.82
     Devine
    -0.76
     estimés
    -0.73
     Kolo
    -0.73
     Walters
    -0.73
    UVWXYZ
    -0.70
     Pelicans
    -0.70
    Sylvie
    -0.69
     Rece
    -0.69
    POSITIVE LOGITS
    atimes
    0.81
    =?";
    0.81
     useAppContext
    0.76
     chords
    0.75
    gher
    0.74
    McLaren
    0.73
     Koh
    0.73
     Uber
    0.73
    Moh
    0.72
     Sober
    0.72
    Activations Density 0.058%

    No Known Activations