© 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. 1166
    Prev
    Next
    INDEX
    Explanations

    references to specific types of arrangements or contracts in a legal or professional context

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

    "...on a [something]-by-[something] basis."

    np_acts-logits-general · gemini-2.0-flash

    X basis

    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
    MENAFN
    -0.75
     насељу
    -0.63
    !*\
    -0.62
    satunya
    -0.61
     tabPage
    -0.59
    queryInterface
    -0.59
    Diwedd
    -0.54
    reactstrap
    -0.54
    ladel
    -0.52
     IMDG
    -0.51
    POSITIVE LOGITS
     basis
    1.70
    basis
    1.36
     Basis
    1.33
    Basis
    1.28
     BASIS
    1.17
     bases
    1.13
    Bases
    0.88
    bases
    0.86
     Bases
    0.84
     basi
    0.82
    Activations Density 0.139%

    No Known Activations