© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 98831
    Prev
    Next
    INDEX
    Explanations

    references to beans in various contexts, likely related to programming or configuration settings

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

    java beans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fisk
    -0.41
     Murray
    -0.41
     Mackay
    -0.40
     élect
    -0.40
     Gil
    -0.38
    Murray
    -0.38
    Gil
    -0.37
     Smyth
    -0.37
    uk
    -0.37
    Invitrogen
    -0.37
    POSITIVE LOGITS
    beans
    3.36
    Beans
    2.39
     beans
    2.27
     Beans
    2.25
    bean
    1.80
     bean
    1.77
     Bean
    1.69
    Bean
    1.63
    BEAN
    1.58
    getBean
    1.14
    Activations Density 0.000%

    No Known Activations