© 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. 21-GEMMASCOPE-RES-16K
    11. 13600
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeografia
    -0.96
    oa̍t
    -0.92
     autorytatywna
    -0.90
     мәкал
    -0.90
     Administrativna
    -0.88
     linkovi
    -0.87
    хьтан
    -0.85
     gynhyrchwyd
    -0.83
     Мексичка
    -0.81
    expandindo
    -0.80
    POSITIVE LOGITS
    {~
    0.28
     spéc
    0.27
    ập
    0.25
    हाय
    0.24
     bottoms
    0.24
     y
    0.24
    ค้า
    0.24
    1
    0.23
     automaton
    0.23
     buffered
    0.23
    Activations Density 1.125%

    No Known Activations