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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 3333
    Prev
    Next
    INDEX
    Explanations

    references to structured content or tables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.84
     Мексичка
    -0.71
    WithIOException
    -0.71
    ReusableCell
    -0.68
    Diwedd
    -0.67
    Geplaatst
    -0.67
     referrerpolicy
    -0.65
    +#+#
    -0.65
     تضيفلها
    -0.63
     AttributeSet
    -0.62
    POSITIVE LOGITS
     Contents
    1.52
    Contents
    1.51
    CONTENTS
    1.40
     contents
    1.39
    contents
    1.34
    Table
    1.31
     Table
    1.29
     CONTENTS
    1.28
     Introduction
    1.24
     table
    1.23
    Activations Density 0.444%

    No Known Activations