© 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. 2-GEMMASCOPE-RES-16K
    6. 7526
    Prev
    Next
    INDEX
    Explanations

    terms related to architecture and the concept of 'arch'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیکھیے
    -0.40
     mortgage
    -0.39
     hose
    -0.38
     interface
    -0.38
     rootView
    -0.38
     forcible
    -0.36
     bağlantılar
    -0.36
     snake
    -0.36
     Gordon
    -0.36
     ferry
    -0.35
    POSITIVE LOGITS
     Arch
    1.29
    Arch
    1.25
    arch
    1.20
     arch
    1.18
    ARCH
    0.94
     ARCH
    0.94
     arches
    0.91
     Architects
    0.80
     Arches
    0.79
    Архи
    0.79
    Activations Density 0.274%

    No Known Activations