© 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. 31-GEMMASCOPE-RES-16K
    11. 5962
    Prev
    Next
    INDEX
    Explanations

    references to water and drinking activities

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

    phrases involving administering substances to animals via drinking water.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hash
    -0.41
     hash
    -0.39
    Hash
    -0.36
     Wax
    -0.35
     ma
    -0.32
     Hash
    -0.30
     fer
    -0.30
    κης
    -0.30
     Comput
    -0.30
     wax
    -0.30
    POSITIVE LOGITS
     drinking
    1.70
     water
    1.67
    drinking
    1.52
    Drinking
    1.51
     Drinking
    1.51
     drink
    1.45
     potable
    1.40
     Water
    1.37
    Water
    1.36
     DRINK
    1.36
    Activations Density 0.195%

    No Known Activations