© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10126
    Prev
    Next
    INDEX
    Explanations

    references to electronic hardware and software specifications

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

    Operating systems, especially MacOS

    np_acts-logits-general · gemini-2.0-flash

    operating systems and software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     disambiguazione
    -0.39
     unreliable
    -0.35
     disponibilités
    -0.35
     reutiliz
    -0.35
    IntoConstraints
    -0.35
    RELATIVE
    -0.34
    tagext
    -0.34
    feier
    -0.34
     Auß
    -0.32
     муніципалі
    -0.31
    POSITIVE LOGITS
    sizeCache
    0.55
    outState
    0.54
     يتيمه
    0.53
     software
    0.52
     OMITBAD
    0.50
    initializeApp
    0.49
     firmware
    0.48
    EIF
    0.48
     lda
    0.48
    ☸
    0.48
    Activations Density 0.382%

    No Known Activations