© 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. 37-GEMMASCOPE-RES-16K
    11. 4915
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cors
    -0.40
     cn
    -0.40
     catholic
    -0.40
     chrysler
    -0.39
     chelsea
    -0.39
     congress
    -0.38
    cq
    -0.38
     cq
    -0.38
     commonwealth
    -0.37
     camb
    -0.37
    POSITIVE LOGITS
     Car
    0.87
     Cur
    0.86
     Cos
    0.83
     Cot
    0.82
     Cost
    0.81
     Con
    0.81
     Cut
    0.80
     Cou
    0.80
     Cer
    0.80
     Can
    0.80
    Activations Density 0.949%

    No Known Activations