© 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. 812
    Prev
    Next
    INDEX
    Explanations

    references to large quantities or numbers

    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
    +0.09
    0.4%
    783
    +0.05
    0.2%
    1265
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    864
    +0.09
    0.05
    824
    +0.05
    0.05
    282
    +0.05
    0.05
    Negative Logits
    <bos>
    -1.33
    
    -0.87
    /**
    -0.81
    /***
    -0.81
    ⓧ
    -0.80
    <?
    -0.77
    /*
    -0.69
    <?
    -0.67
    public
    -0.62
    <!--
    -0.62
    POSITIVE LOGITS
     millions
    1.61
     stockholm
    1.56
     Millions
    1.55
     Juf
    1.51
     maneu
    1.50
    millions
    1.50
     hcm
    1.49
     billions
    1.44
     bandung
    1.40
     napoli
    1.39
    Activations Density 0.105%

    No Known Activations