© 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. 886
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and related terms

    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
    +0.15
    0.7%
    1978
    +0.10
    0.5%
    382
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.15
    0.22
    382
    +0.10
    0.16
    478
    +0.06
    -0.01
    Negative Logits
    <bos>
    -2.82
    ⓧ
    -1.21
    /**
    -1.09
    
    -1.08
    /***
    -1.03
    <?
    -0.98
    ///**
    -0.87
    /*
    -0.79
    <?
    -0.78
     /**
    -0.73
    POSITIVE LOGITS
     véhic
    1.09
     sappi
    0.94
     Minang
    0.94
     délib
    0.94
     quoique
    0.94
     soulign
    0.88
     bandung
    0.87
     cæ
    0.87
     tramont
    0.86
     rafra
    0.85
    Activations Density 1.442%

    No Known Activations