© 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 EvalsExportsinterp-engineNEWAPI 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. 4081
    Prev
    Next
    INDEX
    Explanations

    references to time and duration in research contexts

    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
    WithIdentifier
    -0.65
     cheminée
    -0.59
     quidem
    -0.58
    таратура
    -0.57
    niosek
    -0.57
    RoutingModule
    -0.56
    WAUKEE
    -0.54
    "}";
    -0.54
     "}";
    -0.53
    reactstrap
    -0.53
    POSITIVE LOGITS
     throughout
    0.93
     across
    0.89
    throughout
    0.88
    across
    0.84
    Across
    0.83
     Across
    0.82
     ACROSS
    0.80
     Throughout
    0.79
    Throughout
    0.74
     span
    0.74
    Activations Density 0.141%

    No Known Activations