© 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. 5-GEMMASCOPE-RES-16K
    11. 2900
    Prev
    Next
    INDEX
    Explanations

    HTTP content types, specifically those related to application data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WaitForSeconds
    -0.77
     Zähne
    -0.74
     jugé
    -0.74
    AuthGuard
    -0.73
     payé
    -0.71
     Solidity
    -0.70
    lwjgl
    -0.70
     verrez
    -0.69
     HDPE
    -0.67
     GenerationType
    -0.66
    POSITIVE LOGITS
     application
    2.35
    application
    2.23
     applications
    2.19
     Application
    2.19
    Application
    2.13
     Applications
    2.01
    Applications
    1.96
    applications
    1.91
    APPLICATION
    1.86
     APPLICATION
    1.77
    Activations Density 0.070%

    No Known Activations