© 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. 27-GEMMASCOPE-RES-16K
    11. 9866
    Prev
    Next
    INDEX
    Explanations

    code-related terms and directives in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DllImport
    -0.43
     '{@
    -0.41
     Мексичка
    -0.39
    DebuggerNonUser
    -0.37
    addContainerGap
    -0.37
    ifolium
    -0.36
    RTCK
    -0.36
     CreateTagHelper
    -0.36
    
    -0.35
    ToBounds
    -0.35
    POSITIVE LOGITS
     here
    2.38
     aquí
    1.78
    here
    1.78
     Here
    1.77
     здесь
    1.72
    Here
    1.70
     aqui
    1.62
     disini
    1.56
     aici
    1.56
     HERE
    1.55
    Activations Density 0.480%

    No Known Activations