© 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. 9-GEMMASCOPE-RES-16K
    11. 14553
    Prev
    Next
    INDEX
    Explanations

    references to prizes and bonuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.93
    JspWriter
    -0.78
    andaş
    -0.73
    EndTag
    -0.72
    complexType
    -0.71
    LookAnd
    -0.69
    PyExc
    -0.68
     pantalon
    -0.68
    stateProvider
    -0.68
    ircut
    -0.67
    POSITIVE LOGITS
     delight
    0.94
     TREAS
    0.90
     Schatz
    0.89
     joys
    0.88
     trésor
    0.86
     Pleasure
    0.85
     treasure
    0.85
     pleasure
    0.79
     delights
    0.78
     Bonus
    0.78
    Activations Density 0.082%

    No Known Activations