© 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. 4431
    Prev
    Next
    INDEX
    Explanations

    definitions and references to programming interfaces

    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
     chré
    -0.88
     sauvages
    -0.88
     ExecuteAsync
    -0.86
     dépens
    -0.81
    dhury
    -0.80
     Romains
    -0.79
     Tyrol
    -0.78
     noires
    -0.77
     meurt
    -0.77
     zirc
    -0.76
    POSITIVE LOGITS
     interfaces
    1.29
    Interface
    1.17
    Interfaces
    1.14
     interface
    1.12
     Interface
    1.05
     Interfaces
    1.02
    interfaces
    1.01
     INTERFACE
    1.01
    INTERFACE
    1.00
    interface
    0.97
    Activations Density 0.058%

    No Known Activations