© 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. 0-GEMMASCOPE-RES-16K
    6. 10104
    Prev
    Next
    INDEX
    Explanations

    references to parallelism in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alyptus
    -0.54
    Bent
    -0.50
     NOS
    -0.50
     AssemblyCompany
    -0.49
    bent
    -0.49
    rxjs
    -0.48
    :✨
    -0.47
    cement
    -0.45
     substanti
    -0.45
    寸
    -0.45
    POSITIVE LOGITS
     prisoners
    0.96
     prisonniers
    0.84
     prisoner
    0.82
     prision
    0.82
     Prisoners
    0.77
     PRISON
    0.77
     Gefang
    0.73
    Prison
    0.67
     Prisoner
    0.66
     Gefäng
    0.65
    Activations Density 0.253%

    No Known Activations