© 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. 24-GEMMASCOPE-RES-16K
    11. 767
    Prev
    Next
    INDEX
    Explanations

    manual coding structures, including programming language syntax and declarations

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

    Immediately follows "namespace"

    np_acts-logits-general · gemini-2.0-flash

    C++ namespaces and code constructs

    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
     R
    -0.35
    hline
    -0.34
    here
    -0.32
     wear
    -0.31
    ComponentModel
    -0.31
    see
    -0.31
    
    -0.31
     Wear
    -0.31
    are
    -0.30
    aut
    -0.30
    POSITIVE LOGITS
    Personendaten
    0.83
     препратки
    0.77
    ьаж
    0.65
     ProtoMessage
    0.65
    expandindo
    0.64
     الرياضيه
    0.64
    ftagPool
    0.63
    RenderAtEndOf
    0.63
    invokeLater
    0.62
     Мексичка
    0.60
    Activations Density 0.045%

    No Known Activations