© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3564
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to mechanical failure and interactions in devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    قایناق‌لار
    -0.54
    AnimationsModule
    -0.52
    InjectAttribute
    -0.46
    enderror
    -0.46
     ainfi
    -0.45
    astify
    -0.44
     Reserv
    -0.43
     queima
    -0.43
    imageshack
    -0.42
    Reserv
    -0.42
    POSITIVE LOGITS
     detach
    1.08
     detachment
    1.05
     detached
    1.00
     ripped
    0.91
     loose
    0.86
     ripping
    0.85
     cracking
    0.85
     loosened
    0.83
     tearing
    0.83
     cracked
    0.83
    Activations Density 0.606%

    No Known Activations