© 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. 14821
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structures related to JSON manipulation and error handling

    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
    httphttps
    -0.75
    Географиясе
    -0.65
    RTEX
    -0.53
     Numerade
    -0.48
     Rath
    -0.46
    :✨
    -0.44
    twimg
    -0.43
     Tad
    -0.43
    Rüyada
    -0.43
    TagMode
    -0.43
    POSITIVE LOGITS
     obj
    2.38
    obj
    2.09
    Obj
    1.43
     objective
    1.38
     Obj
    1.37
    objective
    1.13
     Objective
    1.06
     obje
    1.05
     objec
    1.03
     OBJ
    1.02
    Activations Density 0.147%

    No Known Activations