© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4373
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authorship and contributions in a research context

    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
    TagMode
    -0.47
    気持ちが
    -0.35
     Bim
    -0.33
     dars
    -0.32
    TEP
    -0.29
     Karab
    -0.28
     ced
    -0.28
     regular
    -0.28
     uuidv
    -0.28
     toege
    -0.28
    POSITIVE LOGITS
     Zhang
    1.10
     Wang
    1.07
     Liu
    1.00
     Chen
    0.99
    Wang
    0.94
    Zhang
    0.94
     Li
    0.91
    Liu
    0.88
     Huang
    0.87
    Chen
    0.87
    Activations Density 0.262%

    No Known Activations