© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1035
    Prev
    Next
    INDEX
    Explanations

    instructions or tips related to physical activity and wellness

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.11
    0.4%
    1026
    +0.05
    0.2%
    1352
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.11
    0.03
    446
    +0.05
    0.03
    664
    +0.05
    0.03
    Negative Logits
    <bos>
    -1.98
    /***
    -1.01
    ///**
    -0.78
     /**
    -0.67
    /*!
    -0.66
    //@
    -0.64
    //{
    -0.62
    //*/
    -0.61
    //---
    -0.60
    protected
    -0.59
    POSITIVE LOGITS
     maneu
    0.97
     wikihow
    0.93
     maroc
    0.93
     eduardo
    0.91
     Minang
    0.90
     roberto
    0.89
     outlander
    0.88
     véhic
    0.87
     beverly
    0.86
     jorge
    0.83
    Activations Density 0.107%

    No Known Activations