© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5816
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to instances in programming or object-oriented concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CURLOPT
    -0.85
     Betts
    -0.77
     regata
    -0.71
     Cowper
    -0.70
     preocupes
    -0.70
     marl
    -0.69
     deberes
    -0.67
     CDA
    -0.67
     brim
    -0.66
     Morley
    -0.66
    POSITIVE LOGITS
    Instance
    1.51
     Instance
    1.41
    instances
    1.35
    Instances
    1.32
     instance
    1.32
    instance
    1.28
     Instances
    1.26
     instances
    1.22
    getInstance
    1.21
     getInstance
    1.16
    Activations Density 0.084%

    No Known Activations