© 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. 18-GEMMASCOPE-RES-16K
    11. 8086
    Prev
    Next
    INDEX
    Explanations

    HTML tags and formatting elements

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

    "contents", often capitalized

    np_acts-logits-general · gemini-2.0-flash

    table of contents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.76
    GraphicsUnit
    -0.73
    DoubleQuotes
    -0.67
     Мексичка
    -0.67
     незавершена
    -0.66
    RenderAtEndOf
    -0.65
    íncia
    -0.63
     AttributeSet
    -0.63
     Roskov
    -0.62
    +#+#
    -0.60
    POSITIVE LOGITS
     Contents
    1.58
    Contents
    1.54
     contents
    1.50
    CONTENTS
    1.44
     Table
    1.42
    Table
    1.42
     table
    1.41
    contents
    1.39
     CONTENTS
    1.33
    TABLE
    1.26
    Activations Density 0.399%

    No Known Activations