© 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. 36-GEMMASCOPE-RES-16K
    11. 14585
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.78
    PyExc
    -0.76
    <pad>
    -0.69
    <unused43>
    -0.69
     ſte
    -0.68
    <unused41>
    -0.68
    <unused42>
    -0.67
    <unused74>
    -0.67
    <unused76>
    -0.67
     ſche
    -0.67
    POSITIVE LOGITS
    if
    0.74
     Segurança
    0.43
     rechazar
    0.40
     cromado
    0.37
     commandés
    0.37
    switch
    0.35
     afuera
    0.35
    ที่จะ
    0.35
     Saúde
    0.34
     alrededores
    0.34
    Activations Density 0.090%

    No Known Activations