© 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. 16-GEMMASCOPE-RES-16K
    6. 13331
    Prev
    Next
    INDEX
    Explanations

    various programming and technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.74
    ]")]
    -0.60
     kasarigan
    -0.59
     Italijani
    -0.55
    qü
    -0.52
     idéia
    -0.51
    balleur
    -0.51
     Miß
    -0.50
    ValueGeneration
    -0.47
    MemoryWarning
    -0.46
    POSITIVE LOGITS
    StandardCharsets
    0.70
     microbiome
    0.69
    GetMapping
    0.69
    令和
    0.68
    PYX
    0.67
     covid
    0.64
    ChildScrollView
    0.62
     pandemia
    0.60
    nullptr
    0.59
     TMPro
    0.59
    Activations Density 3.561%

    No Known Activations