© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 16183
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to computer programming and engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Millard
    -0.96
     Emory
    -0.93
     viață
    -0.86
    Berikut
    -0.84
    География
    -0.83
     Berikut
    -0.82
     cach
    -0.81
     McMillan
    -0.80
     acrylique
    -0.79
     Washburn
    -0.79
    POSITIVE LOGITS
    theless
    1.18
     licences
    1.05
    alisation
    0.97
     Auk
    0.95
     Adviser
    0.92
     doughnuts
    0.92
    nastics
    0.92
    UserScript
    0.90
     Tsar
    0.87
     practised
    0.87
    Activations Density 2.519%

    No Known Activations