© 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. 11-GEMMASCOPE-RES-16K
    11. 11039
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers or labels that include the keyword "num."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \}\\
    -0.81
     '/';
    -0.74
    ]+=
    -0.74
    ®:
    -0.74
    ]]]
    -0.73
    "){
    -0.72
    branche
    -0.72
     Vivi
    -0.72
    колеп
    -0.71
    ">:
    -0.71
    POSITIVE LOGITS
    Num
    1.30
    num
    1.29
     num
    1.29
     nums
    1.24
    setNum
    1.20
     Num
    1.19
    nums
    1.15
    NUM
    1.13
    numRows
    1.10
    Nums
    1.10
    Activations Density 0.067%

    No Known Activations