© 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. 3-GEMMASCOPE-RES-16K
    11. 5913
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Ton" and its variations along with related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     localObject
    -0.72
    quiel
    -0.71
    robial
    -0.70
    ethene
    -0.69
    ciful
    -0.68
    /***/
    -0.68
     Superhosts
    -0.68
    ocrine
    -0.67
    (;;)
    -0.66
    horizontalLayout
    -0.66
    POSITIVE LOGITS
     ton
    3.06
    ton
    2.97
     Ton
    2.80
    Ton
    2.75
     TON
    2.62
    TON
    2.61
     tons
    2.22
     Tons
    2.10
    tons
    2.10
    Tons
    2.04
    Activations Density 0.126%

    No Known Activations