© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 3892
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers or symbols related to mathematical equations or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.94
    сти
    -0.81
    ]>
    -0.81
    strick
    -0.80
    makeConstraints
    -0.79
    getBlock
    -0.78
     Gatt
    -0.76
    ści
    -0.76
     nos
    -0.75
    ogonal
    -0.74
    POSITIVE LOGITS
    ,\
    1.48
    .\
    1.38
    :\
    1.24
    ).\
    1.22
    -\
    1.12
    ',\
    1.06
    ;\
    1.06
    ?\
    1.04
     .\
    1.04
    {\
    1.03
    Activations Density 0.147%

    No Known Activations