© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1452
    Prev
    Next
    INDEX
    Explanations

    content related to companies and their descriptions

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

    before "is a" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    entity descriptions

    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
     يتيمه
    -0.70
     kasarigan
    -0.70
     مشين
    -0.67
    KommentareTeilen
    -0.67
     مرئيه
    -0.66
    Дереккөздер
    -0.65
     Numerade
    -0.64
    forChild
    -0.64
    انيف
    -0.63
     estekak
    -0.62
    POSITIVE LOGITS
     chiefly
    0.34
     surla
    0.33
     Wikipedia
    0.32
     primarily
    0.31
     cappuccio
    0.30
     principalement
    0.29
     Notably
    0.29
    争议
    0.29
    kově
    0.28
    RegistryLite
    0.28
    Activations Density 1.680%

    No Known Activations