© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1327
    Prev
    Next
    INDEX
    Explanations

    references to environmental issues, particularly related to water quality and contamination

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

    Drinking water sources and contamination

    np_acts-logits-general · gemini-2.0-flash

    drinking water systems and sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Composable
    -0.59
     Immigration
    -0.56
     hornet
    -0.55
     Airways
    -0.53
    Porsche
    -0.53
    PreferredItem
    -0.52
    Immigration
    -0.51
    QMetaType
    -0.51
     lucifer
    -0.51
    SharedDtor
    -0.50
    POSITIVE LOGITS
     drinking
    1.43
     Drinking
    1.27
    Drinking
    1.19
     water
    1.17
     potable
    1.16
    drinking
    1.15
     DRINK
    1.10
     drink
    1.08
     taps
    1.03
    drink
    1.01
    Activations Density 0.145%

    No Known Activations