© 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. 4741
    Prev
    Next
    INDEX
    Explanations

    components and specifications related to computer hardware, particularly CPUs and coolers

    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
    atschappij
    -0.52
    ftagPool
    -0.50
    ➯
    -0.49
    WillAppear
    -0.47
    flashdata
    -0.45
     MainAxisSize
    -0.44
     okuyayım
    -0.42
    ագրություններ
    -0.41
     comunale
    -0.41
    PMailer
    -0.41
    POSITIVE LOGITS
     CPU
    1.24
     processor
    1.23
     processors
    1.19
     cpu
    1.12
     CPUs
    1.09
     Intel
    1.09
    CPU
    1.04
     Processor
    1.03
     Processors
    1.00
    Intel
    0.96
    Activations Density 0.367%

    No Known Activations