© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14697
    Prev
    Next
    INDEX
    Explanations

    various types of mathematical and programming constructs, particularly involving variables and operations

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

    Mathematical/logical notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation with indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    richTextPanel
    -0.52
     intptr
    -0.49
    ViewFeatures
    -0.48
    にほんブログ村
    -0.44
     Paglinawan
    -0.43
     Geſch
    -0.43
     allies
    -0.43
     cheats
    -0.42
     careers
    -0.42
    éraires
    -0.42
    POSITIVE LOGITS
    MockBean
    0.39
     vœux
    0.38
     Turquía
    0.38
    MIPS
    0.36
    HasForeignKey
    0.35
    ContentLoaded
    0.35
     Komunikasi
    0.34
    mektedir
    0.33
     Jurí
    0.33
    odziel
    0.32
    Activations Density 0.530%

    No Known Activations