© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 9110
    Prev
    Next
    INDEX
    Explanations

    structured comments and documentation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Weldon
    -0.39
     Edison
    -0.39
     saites
    -0.38
    enson
    -0.37
    ṳ
    -0.36
     Jody
    -0.35
    ỏng
    -0.34
     Radon
    -0.33
     Levinson
    -0.33
     ,,
    -0.33
    POSITIVE LOGITS
    ****************
    0.86
    ******
    0.68
     Asturias
    0.68
    ****
    0.66
    ************
    0.66
     المعيارى
    0.65
    ***********
    0.65
    ***************
    0.64
    **************
    0.63
    *******
    0.62
    Activations Density 2.249%

    No Known Activations