© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12415
    Prev
    Next
    INDEX
    Explanations

    terms related to water, water quality, water purification, and water supply in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    755
    +0.15
    0.6%
    577
    +0.14
    0.5%
    893
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    755
    +0.15
    0.05
    1565
    +0.14
    0.04
    577
    +0.12
    0.04
    Negative Logits
     lascia
    -0.51
     pollut
    -0.51
     farà
    -0.48
     conosce
    -0.48
     intende
    -0.47
     unve
    -0.47
     gioca
    -0.46
     racconta
    -0.46
     riesce
    -0.46
     aiuta
    -0.46
    POSITIVE LOGITS
     water
    1.33
    water
    1.28
     WATER
    1.23
    Water
    1.22
     Water
    1.22
    WATER
    1.16
     waters
    1.05
     Waterman
    1.03
    Wasser
    0.94
     Wasser
    0.91
    Activations Density 0.119%

    No Known Activations