© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 5965
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and expressions, particularly related to estimators and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.94
     myſelf
    -0.85
    ſelf
    -0.81
     Majefty
    -0.76
     мәкал
    -0.76
     Jefus
    -0.76
    __(/*!
    -0.76
     дописавши
    -0.74
     pleaſure
    -0.72
     itſelf
    -0.70
    POSITIVE LOGITS
     ste
    0.47
     Ste
    0.45
    TestFixture
    0.45
    setAuto
    0.43
     l
    0.42
    itex
    0.42
     li
    0.42
    derna
    0.40
     L
    0.39
     discutir
    0.39
    Activations Density 0.777%

    No Known Activations