© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8896
    Prev
    Next
    INDEX
    Explanations

    references to lists and enumerations within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     environment
    -0.42
    AppContext
    -0.40
     ​​
    -0.37
     Sha
    -0.35
     entorno
    -0.35
    April
    -0.34
     Within
    -0.34
     adaptar
    -0.34
     ambiente
    -0.34
     During
    -0.33
    POSITIVE LOGITS
     list
    1.20
     lists
    1.05
     Liste
    1.04
     liste
    1.02
     lista
    1.01
     список
    0.97
    清单
    0.96
     List
    0.94
     Lists
    0.92
     seznam
    0.90
    Activations Density 0.180%

    No Known Activations