© 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. 2-GEMMASCOPE-RES-16K
    11. 8387
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.92
    Nuorodos
    -0.81
    Referencie
    -0.78
     InputDecoration
    -0.78
     propOrder
    -0.77
    ^(@)
    -0.75
    קישורים
    -0.75
    Geplaatst
    -0.74
    printLine
    -0.74
    kháu
    -0.74
    POSITIVE LOGITS
     parte
    0.95
     part
    0.88
    part
    0.78
     частью
    0.76
     the
    0.71
    část
    0.68
     Bestandteil
    0.67
     partie
    0.64
    的一部分
    0.64
    částí
    0.63
    Activations Density 0.186%

    No Known Activations