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

    Neuronpedia

    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 - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 14016
    Prev
    Next
    INDEX
    Explanations

    instances of "DOCTYPE" declarations and relevant HTML or XML structural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    class
    -0.50
     personal
    -0.48
     (
    -0.48
     Personal
    -0.46
     $
    -0.45
     g
    -0.43
     serra
    -0.43
     d
    -0.42
    panic
    -0.42
    прав
    -0.42
    POSITIVE LOGITS
    ;#
    4.26
     disambiguazione
    1.18
    ArrowToggle
    1.08
     surla
    1.04
    مصادر
    1.03
    IntoConstraints
    1.01
     estekak
    0.99
    contentLoaded
    0.98
    ConstraintMaker
    0.93
     Autorizaciones
    0.93
    Activations Density 0.039%

    No Known Activations