© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1008
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical assembly and components

    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
    ciamento
    -0.41
    🔀
    -0.39
     referenties
    -0.39
    Devin
    -0.38
     Devin
    -0.38
    ModelAttribute
    -0.38
    Sweep
    -0.37
     sweep
    -0.36
     initComponents
    -0.36
    QPalette
    -0.35
    POSITIVE LOGITS
     holes
    2.11
     hole
    2.08
     drill
    1.91
     drilling
    1.89
     drilled
    1.88
     Hole
    1.85
    Hole
    1.81
     Holes
    1.74
    holes
    1.73
    Holes
    1.72
    Activations Density 0.713%

    No Known Activations