© 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. 738
    Prev
    Next
    INDEX
    Explanations

    phrases related to amenities and attractions in a hotel or resort setting

    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
    504
    +0.07
    0.2%
    168
    +0.06
    0.2%
    366
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.01
    1061
    +0.06
    0.03
    1557
    +0.06
    0.02
    Negative Logits
    /**
    -0.74
    /*
    -0.71
    
    -0.66
    <?
    -0.66
    /*!
    -0.59
    <?
    -0.58
    /***
    -0.56
     get
    -0.52
     try
    -0.50
     who
    -0.50
    POSITIVE LOGITS
    side
    1.94
    SIDE
    1.25
    Side
    1.06
     swarovski
    1.03
    sides
    1.00
     ftre
    0.96
     ftu
    0.95
     Jambi
    0.95
     Augu
    0.95
     Juf
    0.93
    Activations Density 0.195%

    No Known Activations