© 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. 12310
    Prev
    Next
    INDEX
    Explanations

    phrases related to interactions and their complexities

    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
    zd
    -0.68
     Zend
    -0.61
     Vod
    -0.60
    ншни
    -0.60
     tetto
    -0.59
     Ston
    -0.59
     CommonModule
    -0.57
     тому
    -0.57
    zus
    -0.57
     grasas
    -0.56
    POSITIVE LOGITS
     interaction
    2.17
     interactions
    2.10
     Interaction
    2.10
    Interaction
    1.97
     interact
    1.96
     Interactions
    1.94
    interaction
    1.94
     Interact
    1.91
    Interactions
    1.84
     interacted
    1.83
    Activations Density 0.075%

    No Known Activations