© 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. 34-GEMMASCOPE-RES-16K
    6. 10970
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and syntax associated with function definitions in C++

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arraycopy
    -0.68
    webElement
    -0.55
     '\\;'
    -0.55
    AddTagHelper
    -0.54
     invokingState
    -0.53
    CGRectMake
    -0.50
     AssemblyCompany
    -0.49
    DoubleQuotes
    -0.49
     betweenstory
    -0.49
     متعلقه
    -0.49
    POSITIVE LOGITS
     char
    0.65
    char
    0.63
    const
    0.63
     void
    0.59
    void
    0.59
     const
    0.52
     unsigned
    0.52
    unsigned
    0.51
     std
    0.50
    std
    0.45
    Activations Density 0.354%

    No Known Activations