© 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. 88
    Prev
    Next
    INDEX
    Explanations

    text related to legal documents and administrative proceedings

    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%
    1178
    +0.09
    0.4%
    156
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    327
    +0.09
    0.04
    503
    +0.09
    0.03
    1178
    +0.07
    0.03
    Negative Logits
    
    
    -0.95
    <bos>
    -0.89
    <?
    
    -0.88
    ⓧ
    -0.87
    /**
    -0.83
    <?
    -0.77
    ///**
    -0.72
     république
    -0.65
     incarcer
    -0.63
    /***
    
    -0.62
    POSITIVE LOGITS
     Division
    2.32
    Division
    2.06
     division
    2.01
     DIVISION
    1.90
     Divisions
    1.81
    division
    1.70
     divisions
    1.60
     Div
    1.59
    DIVISION
    1.58
     División
    1.36
    Activations Density 0.159%

    No Known Activations