© 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. 3919
    Prev
    Next
    INDEX
    Explanations

    programming constructs and elements related to data structures or functions

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

    code syntax and programming-related tokens, particularly programming variables and function/method names.

    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
    Tembelea
    -1.01
     autorytatywna
    -0.93
     мәкал
    -0.91
     Roskov
    -0.91
     ویکی‌پدی
    -0.88
     Taktlose
    -0.88
     незавершена
    -0.84
     kasarigan
    -0.84
     @"/
    -0.83
     يتيمه
    -0.77
    POSITIVE LOGITS
     is
    0.31
     =
    0.30
    AL
    0.30
    Slf
    0.29
    J
    0.28
    N
    0.28
     aDecoder
    0.27
    hObject
    0.27
    W
    0.26
    is
    0.25
    Activations Density 0.239%

    No Known Activations