© 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. 0-RES-JB
    6. 740
    Prev
    Next
    INDEX
    Explanations

    references to exclusive or unique entities or services

    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
    +0.08
    0.3%
    1177
    +0.06
    0.2%
    1806
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    244
    +0.08
    0.03
    797
    +0.06
    0.03
    1131
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.08
    //});
    -0.74
    
    
    -0.71
    ⓧ
    -0.70
    ///**
    -0.69
    /***
    
    -0.69
    //};
    -0.67
    <?
    
    -0.66
    /**
    -0.65
    ValueGenerated
    -0.61
    POSITIVE LOGITS
     exclusively
    2.07
     Exclu
    1.54
    exclu
    1.45
     solely
    1.40
    Exclu
    1.25
     eksklu
    1.25
     exclusives
    1.23
     stockholm
    1.21
     exclusive
    1.20
     exclusivement
    1.17
    Activations Density 0.100%

    No Known Activations