© 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. 15-GEMMASCOPE-RES-16K
    11. 5610
    Prev
    Next
    INDEX
    Explanations

    references to data structures and collections in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.80
    fø
    -0.64
    SuccessListener
    -0.61
     Devlin
    -0.60
     @"/
    -0.60
     komer
    -0.58
     pesce
    -0.57
    enterOuterAlt
    -0.57
     renseignements
    -0.57
     Acceptance
    -0.56
    POSITIVE LOGITS
    Collections
    2.00
     Collections
    1.46
     collections
    1.19
    collections
    1.05
     collection
    0.89
     Collection
    0.82
    InputBorder
    0.79
    Collection
    0.78
    collection
    0.72
    ineno
    0.71
    Activations Density 0.010%

    No Known Activations