© 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. 16-GEMMASCOPE-RES-16K
    11. 13260
    Prev
    Next
    INDEX
    Explanations

    descriptions of unique, handcrafted products and their qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    decorative items or decorations

    np_acts-logits-general · gemini-2.0-flash

    decorative craft embellishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.79
    medriver
    -0.71
    reportWebVitals
    -0.68
    fastjson
    -0.65
    куртка
    -0.63
     CreateTagHelper
    -0.63
    CloseOperation
    -0.62
    хьтан
    -0.62
    issauga
    -0.60
    IntoConstraints
    -0.59
    POSITIVE LOGITS
     decorative
    1.00
     Decorative
    0.81
     decoration
    0.80
     decorate
    0.78
     decorating
    0.77
    decorative
    0.77
     dekor
    0.76
     decorativa
    0.74
     decorativos
    0.72
     décor
    0.72
    Activations Density 0.155%

    No Known Activations