© 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. 9-GEMMASCOPE-RES-16K
    11. 8474
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and their structured forms in theoretical content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical expressions where the word "form" appears, especially when introducing formulas, equations, or expressions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PMailer
    -0.66
    sizeCache
    -0.63
     snippetHide
    -0.57
    RenderAtEndOf
    -0.57
     насељу
    -0.56
     CreateTagHelper
    -0.54
    WaitGroup
    -0.53
    IBC
    -0.53
    ValueStyle
    -0.51
    ंदीखरीदारी
    -0.50
    POSITIVE LOGITS
     lautet
    0.46
     znaczy
    0.43
     berikut
    0.40
     følgende
    0.40
     следу
    0.39
     entry
    0.39
     formula
    0.38
     totiž
    0.38
    ดัง
    0.38
     seguinte
    0.37
    Activations Density 1.352%

    No Known Activations