© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12797
    Prev
    Next
    INDEX
    Explanations

    components and specifications related to GPUs and their architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.64
    醐
    -0.58
     probiotics
    -0.51
    mazon
    -0.51
     alarma
    -0.50
     romanzo
    -0.50
     jang
    -0.49
    corns
    -0.49
    elang
    -0.49
     colch
    -0.48
    POSITIVE LOGITS
     graphics
    1.12
     Graphics
    0.98
     GPU
    0.96
     card
    0.92
     graphic
    0.91
     cards
    0.90
    Graphics
    0.84
     Cards
    0.83
     Graphic
    0.81
    graphics
    0.80
    Activations Density 0.222%

    No Known Activations