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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2103
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ton"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    testify
    -0.40
     CWE
    -0.40
    美子
    -0.38
    ArrowToggle
    -0.37
    Ծանոթ
    -0.35
     OGS
    -0.35
    อาด
    -0.35
     متعلقه
    -0.34
    SuccessListener
    -0.34
    rabh
    -0.34
    POSITIVE LOGITS
    ton
    2.39
    TON
    2.02
     ton
    1.91
    Ton
    1.82
     Ton
    1.75
     TON
    1.74
    tons
    1.30
    tonne
    1.20
     tonne
    1.17
     tons
    1.07
    Activations Density 0.445%

    No Known Activations