© 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. 20-GEMMASCOPE-RES-16K
    11. 5648
    Prev
    Next
    INDEX
    Explanations

    specific chemical compounds and their related terms in scientific contexts

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

    acronyms and technical scientific terminology, particularly from medical or chemical research contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    scientific or technical abbreviations, particularly those related to chemical compounds, medical technologies, and research terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    acronyms and alphanumeric code-like terms (often all-caps) used as technical, scientific, or branded names.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    abbreviations and acronyms in technical or scientific text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     surla
    -0.82
    featureID
    -0.78
     kaarangay
    -0.77
     مشين
    -0.70
    хьтан
    -0.70
    Jeografia
    -0.70
    ंदीखरीदारी
    -0.69
    LookAnd
    -0.66
     мәкал
    -0.66
    Personendaten
    -0.64
    POSITIVE LOGITS
    horabuena
    0.43
     soldadura
    0.42
     Occidente
    0.39
     colectivos
    0.38
     büy
    0.37
     corações
    0.36
     is
    0.35
     ràng
    0.35
     powst
    0.35
     behövs
    0.35
    Activations Density 0.686%

    No Known Activations