© 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. 28-GEMMASCOPE-RES-16K
    11. 8173
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, functions, and operations in a programming or mathematical context

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

    Mathematical or programming-related symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation, code variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.56
     utafitiHapana
    -0.54
    ViewImports
    -0.54
     Roskov
    -0.52
    ſtance
    -0.49
     ujednoznacz
    -0.46
    weightedMode
    -0.46
    yntaxException
    -0.46
     Ell
    -0.46
    lief
    -0.45
    POSITIVE LOGITS
    씩
    0.49
    锈钢
    0.40
    íses
    0.39
     apporté
    0.39
     tjen
    0.38
     ansatte
    0.37
     setengah
    0.37
     dàng
    0.37
     renouvel
    0.36
    tagHelperRunner
    0.36
    Activations Density 1.177%

    No Known Activations