© 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. 11040
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to parallel computing and scalability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    出版年
    -0.45
    awtextra
    -0.40
     iconLine
    -0.39
    Tembelea
    -0.39
     Lup
    -0.39
    DialogContent
    -0.38
     flecha
    -0.37
    BitConverter
    -0.36
    formik
    -0.36
    webtoken
    -0.36
    POSITIVE LOGITS
    SBATCH
    0.79
     multiprocessing
    0.46
     uLocal
    0.46
     asymptotically
    0.44
     diversi
    0.43
     divisible
    0.42
    cuda
    0.42
     splitting
    0.42
     ceiling
    0.41
     distribu
    0.41
    Activations Density 0.346%

    No Known Activations