© 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. 5-GEMMASCOPE-RES-16K
    11. 15928
    Prev
    Next
    INDEX
    Explanations

    complex mathematical notation and expressions, particularly related to linear algebra and vector spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.59
    SequentialGroup
    -0.59
    ymal
    -0.56
    mici
    -0.55
    Demografia
    -0.55
     agradável
    -0.53
     odkazy
    -0.53
     Malik
    -0.53
    oa̍t
    -0.52
    Externé
    -0.51
    POSITIVE LOGITS
    webElementXpaths
    0.65
    CppMethod
    0.54
    Portály
    0.46
    esModule
    0.46
    льо
    0.45
    DispatchToProps
    0.45
    通販
    0.45
    nissen
    0.45
    InstrumentedTest
    0.43
    ंदीखरीदारी
    0.43
    Activations Density 0.378%

    No Known Activations