© 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. 20-GEMMASCOPE-RES-16K
    11. 10136
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific updates related to software or system performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     basically
    -0.31
     everything
    -0.28
     highly
    -0.27
    ">//
    -0.24
     typically
    -0.23
     almost
    -0.23
    sand
    -0.23
    highly
    -0.23
     true
    -0.22
     kere
    -0.22
    POSITIVE LOGITS
    PerformLayout
    0.93
     linkovi
    0.88
     ligiloj
    0.84
     المعيارى
    0.84
    WriteTagHelper
    0.78
     Administrativna
    0.77
    exitRule
    0.77
    NameInMap
    0.77
     ivelany
    0.76
     estekak
    0.75
    Activations Density 0.861%

    No Known Activations