© 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. 39-GEMMASCOPE-RES-16K
    11. 533
    Prev
    Next
    INDEX
    Explanations

    technical specifications and configurations related to computer hardware

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.47
     MainAxisSize
    -0.43
    éclairage
    -0.41
    flashdata
    -0.41
    WillAppear
    -0.39
    ftagPool
    -0.39
    Derbyniad
    -0.38
    acan
    -0.37
     recreate
    -0.37
    ButterKnife
    -0.36
    POSITIVE LOGITS
     CPU
    1.17
     processor
    1.13
     CPUs
    1.11
     processors
    1.11
     cpu
    1.07
    CPU
    0.98
     Processor
    0.92
    cpu
    0.91
     Processors
    0.90
    processors
    0.85
    Activations Density 0.671%

    No Known Activations