© 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. 4190
    Prev
    Next
    INDEX
    Explanations

    scientific notation and specific formatting elements related to mathematical expressions or functions

    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
    TagMode
    -0.72
    KURZBESCHREIBUNG
    -0.57
    Autoritní
    -0.56
     propOrder
    -0.56
     Отечественной
    -0.56
    ंदीखरीदारी
    -0.54
    parsedMessage
    -0.54
    berdayakan
    -0.53
     بيها
    -0.51
    ajuku
    -0.51
    POSITIVE LOGITS
     Hart
    0.54
    ij
    0.54
    Hart
    0.53
    bf
    0.53
     dri
    0.52
     heter
    0.48
     reservoir
    0.45
     sca
    0.45
     HART
    0.44
    Scanner
    0.43
    Activations Density 0.538%

    No Known Activations