© 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. 25-GEMMASCOPE-RES-16K
    6. 15639
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to quantum mechanics and learning algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.64
    webElementXpaths
    -0.63
    othesis
    -0.58
    anned
    -0.54
     Sab
    -0.51
    Sab
    -0.51
    thern
    -0.51
    tbx
    -0.50
    duled
    -0.50
    RegressionTest
    -0.50
    POSITIVE LOGITS
    parsedMessage
    0.57
    bootstrapcdn
    0.52
    SharedDtor
    0.46
    FormTagHelper
    0.46
    StateException
    0.45
     AssemblyCulture
    0.43
     intptr
    0.43
    MessageTagHelper
    0.42
    webElement
    0.40
    MemoryWarning
    0.40
    Activations Density 0.581%

    No Known Activations