© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5079
    Prev
    Next
    INDEX
    Explanations

    instances of the word "highlight."

    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
    AutoresizingMask
    -0.42
     FetchType
    -0.42
    SharedDtor
    -0.40
     getNum
    -0.39
     FormData
    -0.36
    SBATCH
    -0.36
    CrossRef
    -0.36
    execSQL
    -0.35
    Bibliograf
    -0.34
     CascadeType
    -0.34
    POSITIVE LOGITS
     highlight
    4.09
     Highlight
    3.70
     highlights
    3.69
    Highlight
    3.47
    highlight
    3.42
    highlights
    3.25
     Highlights
    3.23
     highlighting
    3.16
     highlighted
    3.09
    Highlights
    3.05
    Activations Density 0.099%

    No Known Activations