Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3037
    Prev
    Next
    INDEX
    Explanations

    references to supplementary materials and figures in academic texts

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

    "Figure" or "Fig" followed by S and a number

    np_acts-logits-general · gemini-2.0-flash

    supplementary figures

    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
    uegos
    -0.65
    opsida
    -0.62
    XmlAccessType
    -0.60
     kasarigan
    -0.59
    oredCriteria
    -0.54
    __(/*!
    -0.53
    MouseAdapter
    -0.52
    SpringBootTest
    -0.52
    abetes
    -0.50
    adpleegd
    -0.49
    POSITIVE LOGITS
     supplementary
    1.16
     Supplementary
    1.15
     Supplemental
    1.09
    Supplementary
    1.04
     supplemental
    1.01
    Supplemental
    0.96
    SUPPLEMENT
    0.93
     Supplement
    0.92
     SUPPLEMENT
    0.91
    supplement
    0.90
    Activations Density 1.834%

    No Known Activations