© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6814
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations related to linear algebra and vector spaces

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

    mathematical symbols and notation, particularly related to vector spaces, sets, and mathematical typesetting (like $\mathbb{R}$).

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

    mathematical notation, particularly references to vector spaces and set theory with special focus on notation like mathbb{R} for real numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     TestBed
    -0.68
     مرئيه
    -0.60
    findpost
    -0.55
    SourceChecksum
    -0.52
    ंदीखरीदारी
    -0.50
    intios
    -0.49
     zwiſchen
    -0.49
     nakalista
    -0.49
    DataAnnotations
    -0.48
     WebDriverWait
    -0.48
    POSITIVE LOGITS
     indépendante
    0.40
     accesibles
    0.39
     Öffentlichkeit
    0.39
     esclusivamente
    0.39
     regulares
    0.39
     étages
    0.38
     pagrind
    0.37
     læng
    0.36
     realidad
    0.36
    ніципа
    0.36
    Activations Density 0.777%

    No Known Activations