© 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. 15-GEMMASCOPE-RES-16K
    11. 4673
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to water

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mijne
    -0.58
    retudo
    -0.54
     queſta
    -0.52
     zijne
    -0.52
    __(/*!
    -0.52
    ggior
    -0.52
    뀜
    -0.52
     pitä
    -0.51
    ăsp
    -0.51
     montagem
    -0.49
    POSITIVE LOGITS
     Water
    1.35
    Water
    1.35
     water
    1.32
     WATER
    1.23
    water
    1.13
     Wasser
    1.13
    WATER
    1.09
     waters
    1.06
    Wasser
    1.03
     Waters
    1.02
    Activations Density 0.089%

    No Known Activations