© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3113
    Prev
    Next
    INDEX
    Explanations

    references to local produce and dining options

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    high-quality and premium food ingredients and sourcing.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
     Allgemeine
    -0.41
     Stern
    -0.39
     Eriksson
    -0.39
     Iglesias
    -0.38
     avanza
    -0.37
     intermedio
    -0.37
    PropertyType
    -0.37
    寂
    -0.36
     sauve
    -0.36
     Neale
    -0.36
    POSITIVE LOGITS
     freshly
    0.98
     fresh
    0.97
     freshest
    0.96
    fresh
    0.94
     freshness
    0.93
     locally
    0.92
     handcrafted
    0.89
     sourced
    0.88
    sourced
    0.88
     FRESH
    0.85
    Activations Density 0.204%

    No Known Activations