© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 303
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms related to biology and data processing

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

    Tokens followed by numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    phase related terms, numbers, and hubs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日閲覧
    -0.38
    out
    -0.35
    short
    -0.32
    -
    -0.32
    एको
    -0.31
     sì
    -0.31
    imals
    -0.31
    IconModule
    -0.30
     Росси
    -0.30
    cc
    -0.30
    POSITIVE LOGITS
    IntoConstraints
    1.13
     autorytatywna
    1.04
    tanleria
    0.68
    Personendaten
    0.68
     ویکی‌پدی
    0.68
    ьаж
    0.66
    GEBURTSDATUM
    0.63
    Autoritní
    0.62
     يتيمه
    0.61
    EndGlobalSection
    0.61
    Activations Density 1.496%

    No Known Activations