© 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. 23-GEMMASCOPE-RES-16K
    11. 15153
    Prev
    Next
    INDEX
    Explanations

    references to elements in a programming context, particularly related to XML or HTML elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.88
    sizeCache
    -0.84
    lihood
    -0.71
     noires
    -0.71
     Normdatei
    -0.71
     vacacionales
    -0.70
    verifyException
    -0.67
    DispatchToProps
    -0.66
    ClInclude
    -0.64
    schild
    -0.63
    POSITIVE LOGITS
    ally
    0.75
    ations
    0.68
    hasMoreElements
    0.66
    als
    0.66
     himo
    0.65
    alist
    0.58
    ALLY
    0.56
    arian
    0.55
     elements
    0.54
    Elements
    0.53
    Activations Density 0.150%

    No Known Activations