© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 961
    Prev
    Next
    INDEX
    Explanations

    HTML and XML tags along with their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -1.11
    RegressionTest
    -1.09
    хьтан
    -1.02
    webElementXpaths
    -0.94
     disambiguazione
    -0.92
     Administrativna
    -0.91
     ligiloj
    -0.89
    contentLoaded
    -0.86
     OFDb
    -0.84
    SharedDtor
    -0.83
    POSITIVE LOGITS
    mi
    0.67
    enumi
    0.63
     imageNamed
    0.62
    mn
    0.61
    <strong>
    0.61
    mo
    0.60
    /*
    0.57
    <em>
    0.56
    “
    0.56
    <b>
    0.55
    Activations Density 0.068%

    No Known Activations