© 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. 2-GEMMASCOPE-RES-16K
    11. 8344
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and parameters in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mijne
    -0.65
    хьтан
    -0.59
     vastaan
    -0.55
     dumne
    -0.54
     geï
    -0.53
     käytet
    -0.52
     geïsole
    -0.51
    oarece
    -0.49
     gouden
    -0.49
     liitty
    -0.49
    POSITIVE LOGITS
    SequentialGroup
    0.49
     autorytatywna
    0.48
     etc
    0.44
    存于互联网档案馆
    0.43
     Etc
    0.42
    AndEndTag
    0.42
     Xunit
    0.42
    .$.
    0.42
    ClientSize
    0.41
     EU
    0.39
    Activations Density 1.430%

    No Known Activations