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

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 878
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions, particularly related to equations and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     emoji
    -0.48
     constexpr
    -0.44
     https
    -0.44
    styleType
    -0.42
    agnos
    -0.40
     💙
    -0.39
    fastjson
    -0.38
     onboarding
    -0.38
     ❤️
    -0.38
     emojis
    -0.37
    POSITIVE LOGITS
    хьтан
    0.56
    faßt
    0.49
    sizeCache
    0.49
     היתה
    0.45
     ویکی‌پدی
    0.45
    antMatchers
    0.44
     idéia
    0.44
    RTEE
    0.43
     الحره
    0.43
     muß
    0.43
    Activations Density 1.573%

    No Known Activations