© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4568
    Prev
    Next
    INDEX
    Explanations

    programming or code-related elements, particularly focusing on Android-specific components and Java libraries

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

    Code snippets, often involving system calls or error codes

    np_acts-logits-general · gemini-2.0-flash

    syscall.Errno or syscall.Signal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Almost
    -0.37
    Main
    -0.36
    May
    -0.33
    main
    -0.33
    oo
    -0.31
    almost
    -0.31
     almost
    -0.30
    RE
    -0.29
    MAIN
    -0.28
    4
    -0.28
    POSITIVE LOGITS
     كومونز
    1.01
     betweenstory
    0.97
     ſei
    0.96
    transQ
    0.96
    parsedMessage
    0.94
    ésultats
    0.91
     ModelExpression
    0.91
    
    0.90
    setVerticalGroup
    0.90
     ſind
    0.89
    Activations Density 0.416%

    No Known Activations