© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13988
    Prev
    Next
    INDEX
    Explanations

    syntactical structures and function definitions in programming code

    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
    ↵↵
    -0.95
    .
    -0.41
     
    -0.39
    </strong>
    -0.37
    stdarg
    -0.37
    ,
    -0.36
     beyond
    -0.34
     plat
    -0.33
    ↵↵↵
    -0.33
     
    -0.33
    POSITIVE LOGITS
    Personendaten
    0.77
     يتيمه
    0.70
    InstrumentedTest
    0.67
     bankası
    0.66
     desmotivaciones
    0.65
     Italij
    0.63
     Infórmanos
    0.63
    CodeAttribute
    0.63
     bílá
    0.60
    Datuak
    0.59
    Activations Density 0.738%

    No Known Activations