© 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. 3472
    Prev
    Next
    INDEX
    Explanations

    assertions and verification statements in code

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

    Assert statements or expectations

    np_acts-logits-general · gemini-2.0-flash

    testing assertions

    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
    MigrationBuilder
    -1.04
    TagMode
    -0.99
     InputDecoration
    -0.89
     CreateTagHelper
    -0.82
     autorytatywna
    -0.78
     EconPapers
    -0.78
    RenderAtEndOf
    -0.77
    AddTagHelper
    -0.76
     BoxDecoration
    -0.76
     виправивши
    -0.75
    POSITIVE LOGITS
    assertThat
    0.57
    Matchers
    0.42
     llorar
    0.40
    IonicModule
    0.40
     ffilm
    0.39
     miscarriage
    0.39
    jarah
    0.39
    BNL
    0.38
     satisfied
    0.38
     unborn
    0.38
    Activations Density 0.056%

    No Known Activations