© 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. 31-GEMMASCOPE-RES-16K
    11. 3687
    Prev
    Next
    INDEX
    Explanations

    terms related to optimization and minimization in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical notation and technical formulas in academic papers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.49
    rol
    -0.33
    slug
    -0.32
     tier
    -0.31
     cầm
    -0.30
    tablissement
    -0.30
     nest
    -0.30
     Zaman
    -0.30
    lean
    -0.30
    roll
    -0.29
    POSITIVE LOGITS
     minimized
    0.81
     minimization
    0.79
     objective
    0.77
     minimize
    0.71
     función
    0.71
     Objective
    0.70
     function
    0.70
     fitness
    0.69
     minimizing
    0.69
     cost
    0.68
    Activations Density 1.718%

    No Known Activations