© 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. 6302
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data management and processing

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

    fragments of programming code, particularly function calls and method definitions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     ब्रेकडाउन
    -0.76
     Administrativna
    -0.75
     ویکی‌پدی
    -0.70
     Infórmanos
    -0.67
     Meksiku
    -0.66
     CreateTagHelper
    -0.65
    SourceChecksum
    -0.65
     Мексичка
    -0.65
    LookAnd
    -0.64
     Taktlose
    -0.64
    POSITIVE LOGITS
     dne
    0.33
     reutiliz
    0.32
     comis
    0.31
     Läng
    0.29
     jih
    0.29
     wij
    0.29
     sola
    0.28
     matemáticas
    0.28
     ۱۴۰۰
    0.28
     leyenda
    0.27
    Activations Density 0.358%

    No Known Activations