© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13883
    Prev
    Next
    INDEX
    Explanations

    structural and functional elements in programming code, particularly focusing on object-oriented features and functions

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

    function and method definitions in source code.

    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
    WriteTagHelper
    -0.78
    PerformLayout
    -0.76
    ruptedException
    -0.75
    parsedMessage
    -0.74
     defaultstate
    -0.68
    ----</
    -0.66
    errHandler
    -0.66
    addContainerGap
    -0.65
     IBOutlet
    -0.64
    ArgsConstructor
    -0.63
    POSITIVE LOGITS
        
    0.50
            
    0.45
    if
    0.44
    ↵
    0.44
    <blockquote>
    0.41
    ędzy
    0.38
    switch
    0.37
    odi
    0.37
    рио
    0.36
                
    0.36
    Activations Density 0.166%

    No Known Activations