© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 483
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to limits and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yecek
    -0.36
     verschil
    -0.33
    Compat
    -0.31
    hebt
    -0.29
     waard
    -0.29
     Zink
    -0.28
     Bowman
    -0.28
     kapturem
    -0.28
     transported
    -0.28
    NullCheck
    -0.27
    POSITIVE LOGITS
    IntoConstraints
    0.77
    tagHelperRunner
    0.75
    styleType
    0.71
    ValueStyle
    0.70
    webElementXpaths
    0.69
     AssemblyCompany
    0.67
    InitVars
    0.66
    сылкі
    0.66
     ſind
    0.63
     المعيارى
    0.63
    Activations Density 1.858%

    No Known Activations