© 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. 688
    Prev
    Next
    INDEX
    Explanations

    technical issues or challenges within a written document

    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
    +0.12
    0.5%
    1964
    +0.07
    0.3%
    1573
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1596
    +0.12
    0.05
    1964
    +0.07
    0.04
    468
    +0.05
    0.04
    Negative Logits
    <bos>
    -1.87
    /***
    
    -0.79
    /**
    -0.78
    <?
    
    -0.73
    
    
    -0.72
    <?
    -0.72
    #![
    -0.71
    ⓧ
    -0.66
     expel
    -0.64
    /*!
    
    -0.64
    POSITIVE LOGITS
     problem
    1.58
    problem
    1.55
     Problem
    1.52
    Problem
    1.44
     Proble
    1.30
     PROBLEM
    1.28
    PROBLEM
    1.26
     probleme
    1.22
     catég
    1.14
     véhic
    1.10
    Activations Density 0.066%

    No Known Activations