© 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. 9326
    Prev
    Next
    INDEX
    Explanations

    method and variable declarations 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
    endmodule
    -0.50
    WebVitals
    -0.49
     चीज़ों
    -0.47
     pageIndex
    -0.43
     newState
    -0.42
     newList
    -0.42
     viewWillAppear
    -0.42
     screenWidth
    -0.42
     EconPapers
    -0.41
     menuItem
    -0.40
    POSITIVE LOGITS
    super
    0.68
    自己的
    0.58
     savu
    0.56
    this
    0.55
     swojej
    0.53
    assert
    0.52
     svoj
    0.52
     super
    0.52
     kanyang
    0.50
     자신의
    0.50
    Activations Density 0.297%

    No Known Activations