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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6252
    Prev
    Next
    INDEX
    Explanations

    references to "side" or "sides" in various contexts, particularly in relation to discussions about nuances or additional factors in a subject matter

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.52
    хьтан
    -0.41
     frango
    -0.33
     الدولى
    -0.32
    了一种
    -0.32
    getInteger
    -0.32
    testng
    -0.32
    chuhe
    -0.32
     Beng
    -0.31
     Kran
    -0.31
    POSITIVE LOGITS
     side
    4.22
     Side
    3.66
    Side
    3.55
     SIDE
    3.36
    side
    3.22
    SIDE
    2.88
     sides
    2.83
     Sides
    2.41
    sides
    2.41
    サイド
    2.23
    Activations Density 0.115%

    No Known Activations