© 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. 37-GEMMASCOPE-RES-16K
    11. 4589
    Prev
    Next
    INDEX
    Explanations

    code structure and specific data field definitions in programming

    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
    帖最后由
    -0.66
    탤
    -0.57
    下载附件
    -0.55
    ImageContext
    -0.51
     
    -0.48
     متعلقه
    -0.45
     виправивши
    -0.44
     referenties
    -0.44
     noDo
    -0.44
     ModelExpression
    -0.44
    POSITIVE LOGITS
    blank
    0.66
     blank
    0.65
    Blank
    0.59
     null
    0.50
     Blank
    0.50
    verbose
    0.48
     verbose
    0.48
    null
    0.47
    BLANK
    0.45
    unique
    0.43
    Activations Density 0.182%

    No Known Activations