© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 8417
    Prev
    Next
    INDEX
    Explanations

    references to Java Spring framework components, particularly beans and repositories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -1.01
    expandindo
    -1.00
     Monfieur
    -0.96
     myſelf
    -0.92
     fevere
    -0.91
    IBOutlet
    -0.84
     purpoſe
    -0.84
     natale
    -0.82
     Dort
    -0.81
     blessé
    -0.81
    POSITIVE LOGITS
    Bean
    1.61
     Bean
    1.58
     Beans
    1.52
     bean
    1.52
    bean
    1.47
     beans
    1.44
    beans
    1.37
    Beans
    1.32
    BEAN
    1.08
     GENE
    0.97
    Activations Density 0.099%

    No Known Activations