© 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. 12760
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and structures, particularly focusing on class and module definitions, and method invocations

    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
     ujednoznacz
    -0.80
     kaarangay
    -0.72
    copg
    -0.65
     autorytatywna
    -0.65
    IVEREF
    -0.63
    yarnpkg
    -0.63
     الحره
    -0.62
    niſſe
    -0.62
     disambiguazione
    -0.62
    EndGlobalSection
    -0.61
    POSITIVE LOGITS
    .
    0.49
     itself
    0.39
     Förder
    0.38
     Is
    0.37
    对
    0.36
     par
    0.36
     implements
    0.36
    ↵
    0.36
    ui
    0.35
    comp
    0.35
    Activations Density 0.313%

    No Known Activations