© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 5776
    Prev
    Next
    INDEX
    Explanations

    code components related to data structures and their initialization in the Swift programming language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Swift/Protobuf code structure and syntax elements.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.43
    bitField
    -0.43
    oneofs
    -0.37
    QtWidgets
    -0.36
     StringBuffer
    -0.36
    BeginContext
    -0.34
    createClass
    -0.34
     jspb
    -0.34
     ligiloj
    -0.33
     disponibilités
    -0.33
    POSITIVE LOGITS
     SwiftUI
    0.79
     disambiguazione
    0.47
    Portale
    0.45
    
    0.45
    ForEach
    0.45
     protoimpl
    0.44
     ddelweddau
    0.43
     inhal
    0.43
     OMIT
    0.42
     titolata
    0.42
    Activations Density 0.400%

    No Known Activations