© 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. 132
    Prev
    Next
    INDEX
    Explanations

    phrases related to insurance and business services offered by Farmers

    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
    2011
    +0.08
    0.3%
    50
    +0.08
    0.3%
    437
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1865
    +0.08
    0.03
    1718
    +0.08
    0.02
    1669
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.83
     interposed
    -0.66
     endow
    -0.66
    ⓧ
    -0.64
    /***
    -0.62
    <?
    -0.62
    /*!
    -0.62
     overtook
    -0.62
    
    -0.60
    /**
    -0.58
    POSITIVE LOGITS
     Farmers
    1.67
     farmers
    1.58
     farmer
    1.56
    Farmers
    1.52
     Farmer
    1.49
    Farmer
    1.32
    farmers
    1.32
    farmer
    1.28
     cæ
    0.90
     keramik
    0.90
    Activations Density 0.109%

    No Known Activations