© 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. 11874
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and programming syntax elements related to document formatting in coding contexts

    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
     صوتيه
    -0.56
    MessageTagHelper
    -0.54
    مصادر
    -0.49
    richTextPanel
    -0.48
     Tri
    -0.48
     resourceCulture
    -0.46
    optionalTypeArgs
    -0.46
     Ty
    -0.45
     ty
    -0.45
     Red
    -0.44
    POSITIVE LOGITS
    esistenza
    0.42
     fédé
    0.37
     sintética
    0.36
     ferons
    0.35
     Investigaciones
    0.34
     cooperación
    0.33
    ✷
    0.33
    umerable
    0.33
    //}
    0.33
     hormigón
    0.33
    Activations Density 1.088%

    No Known Activations