© 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. 10-GEMMASCOPE-RES-16K
    11. 15602
    Prev
    Next
    INDEX
    Explanations

    elements of programming syntax and structure, specifically related to object-oriented programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     Facultad
    -0.33
     soupe
    -0.32
     sanitarias
    -0.30
     Fiscalía
    -0.30
    ctivos
    -0.28
     maïs
    -0.27
     założ
    -0.27
     Somehow
    -0.27
     Redaktion
    -0.26
     słowa
    -0.26
    POSITIVE LOGITS
     localObject
    1.18
     paramInt
    1.09
    mobileqq
    1.07
    AndEndTag
    0.97
     paramString
    0.91
    SourceChecksum
    0.85
     surla
    0.81
    الحياه
    0.81
    CppMethod
    0.79
     utafitiHapana
    0.77
    Activations Density 0.229%

    No Known Activations