© 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. 70
    Prev
    Next
    INDEX
    Explanations

    information related to contact details such as addresses, phone numbers, and emails

    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
    +0.16
    1.0%
    1978
    +0.11
    0.7%
    1472
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.16
    0.13
    1472
    +0.11
    0.11
    667
    +0.08
    0.08
    Negative Logits
    <bos>
    -2.45
    ⓧ
    -1.10
    /**
    -1.03
    <?
    -1.02
    
    
    -0.94
    <?
    
    -0.89
    /***
    
    -0.86
    /*
    -0.82
    #![
    -0.81
    ///**
    -0.76
    POSITIVE LOGITS
     affor
    1.90
     maneu
    1.79
     increa
    1.76
     stockholm
    1.73
     lidl
    1.70
     embodi
    1.60
     fortn
    1.60
     maroc
    1.60
     inev
    1.60
     strick
    1.60
    Activations Density 0.314%

    No Known Activations