© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5252
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions, specifically focusing on diarrhea symptoms and treatment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    0.8%
    468
    +0.08
    0.3%
    184
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.23
    0.05
    1976
    +0.08
    0.04
    736
    +0.06
    0.05
    Negative Logits
    <bos>
    -2.02
     springfox
    -0.59
    /***
    
    -0.57
     kwiet
    -0.55
    ///**
    -0.53
     defray
    -0.52
    ándor
    -0.52
     ratify
    -0.52
    Kontrola
    -0.49
    <!--
    
    -0.49
    POSITIVE LOGITS
     aen
    0.99
     bandung
    0.88
     magis
    0.84
     ftu
    0.83
     quæ
    0.83
     fta
    0.83
     kasa
    0.83
     marmor
    0.83
     thut
    0.82
     baum
    0.81
    Activations Density 0.366%

    No Known Activations