© 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. 19-GEMMASCOPE-RES-16K
    11. 5294
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and constructs, particularly related to JSON and object management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ष्ण
    -0.54
    erialized
    -0.49
    ContentAsync
    -0.48
    dem
    -0.47
     Ipswich
    -0.47
     gard
    -0.46
    typeorm
    -0.46
    TextHelper
    -0.46
     Nah
    -0.45
    elerik
    -0.45
    POSITIVE LOGITS
    thrift
    1.15
    StructEnd
    1.04
    Thrift
    1.04
     Thrift
    1.02
     thrift
    0.92
     iprot
    0.87
    oprot
    0.80
    iprot
    0.78
    TProtocol
    0.72
     TType
    0.71
    Activations Density 0.098%

    No Known Activations