© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9636
    Prev
    Next
    INDEX
    Explanations

    instances of the word "insert" and its variations in various contexts

    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
     viață
    -0.56
     levens
    -0.50
    WEATHER
    -0.47
    Ethics
    -0.46
     ekos
    -0.46
    getFullYear
    -0.46
    isFile
    -0.45
    getName
    -0.45
    totalPages
    -0.44
     lagerfeld
    -0.44
    POSITIVE LOGITS
    insert
    0.71
     insert
    0.68
    AndroidJUnit
    0.68
     INSERT
    0.66
     noDo
    0.66
     inject
    0.64
    INSERT
    0.63
     inser
    0.62
    makeConstraints
    0.60
     shot
    0.60
    Activations Density 0.141%

    No Known Activations