© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 3659
    Prev
    Next
    INDEX
    Explanations

    references to types of beans and related food items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.50
     Majefty
    -1.38
     Monfieur
    -1.37
     الرياضيه
    -1.33
    expandindo
    -1.23
     itſelf
    -1.21
     Efq
    -1.21
     Allegretto
    -1.17
     ſtate
    -1.14
     Numerade
    -1.13
    POSITIVE LOGITS
     beans
    1.96
     Bean
    1.96
     bean
    1.94
     Beans
    1.92
    Bean
    1.89
    beans
    1.84
    bean
    1.75
    Beans
    1.63
    BEAN
    1.25
    豆
    1.14
    Activations Density 0.070%

    No Known Activations