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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8776
    Prev
    Next
    INDEX
    Explanations

    references to adverse medical events related to dehydration

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

    Hydration and dehydration

    np_acts-logits-general · gemini-2.0-flash

    hydration and dehydration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.58
    reportWebVitals
    -0.50
    enderror
    -0.49
    TemporalType
    -0.47
     BorderSide
    -0.46
    writeFieldEnd
    -0.46
    DidLoad
    -0.44
    fordable
    -0.43
    mpo
    -0.42
    endpush
    -0.42
    POSITIVE LOGITS
     hydration
    1.04
     dehydration
    1.03
    hydration
    0.96
     Hydration
    0.91
     hydrated
    0.88
     hydrating
    0.82
     dehydrated
    0.82
     hydrate
    0.76
     electrolyte
    0.76
     electrolytes
    0.75
    Activations Density 0.437%

    No Known Activations