© 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. 12973
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to modification and editing in code

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

    warnings or instructions that code should not be modified or edited.

    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
     autorytatywna
    -0.39
    новништво
    -0.38
    Insee
    -0.38
    Derbyniad
    -0.35
    ItemBackground
    -0.35
     dale
    -0.33
    klärt
    -0.31
     thiệu
    -0.31
     despedida
    -0.30
     transfieras
    -0.29
    POSITIVE LOGITS
     manually
    3.11
     manual
    2.95
    manual
    2.66
    Manual
    2.58
     Manually
    2.58
     Manual
    2.55
     manuell
    2.53
     manualmente
    2.50
    Manually
    2.39
     manuelle
    2.34
    Activations Density 0.951%

    No Known Activations