© 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. 20-GEMMASCOPE-RES-16K
    11. 3947
    Prev
    Next
    INDEX
    Explanations

    references to data manipulation in a programming context

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

    Code snippets and programming terms

    np_acts-logits-general · gemini-2.0-flash

    electron gun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.79
    HtmlAttribute
    -0.74
    BeginContext
    -0.71
     kasarigan
    -0.68
     CreateTagHelper
    -0.68
     ModelExpression
    -0.64
     acceleration
    -0.63
    aarrggbb
    -0.63
     Acceleration
    -0.62
    LookAnd
    -0.61
    POSITIVE LOGITS
    Dim
    0.51
    بيوتر
    0.47
     Dim
    0.46
    hartt
    0.45
    heça
    0.44
     ostavi
    0.42
     rhestr
    0.42
    ApplicationTests
    0.41
    iço
    0.41
    kijken
    0.41
    Activations Density 0.099%

    No Known Activations