© 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. 6-RES-JB
    11. 4972
    Prev
    Next
    INDEX
    Explanations

    references to physical proximity or nearness

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.27
    1.3%
    889
    +0.09
    0.4%
    1993
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.27
    0.05
    348
    +0.09
    0.04
    1304
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.83
    ⓧ
    -0.86
    <?
    -0.83
    /**
    -0.82
    /*
    -0.78
    #![
    -0.75
    
    -0.72
     continue
    -0.62
    lateinit
    -0.62
     do
    -0.61
    POSITIVE LOGITS
     lele
    1.63
     maroc
    1.48
     hcm
    1.46
     meis
    1.45
     bandung
    1.45
     Minang
    1.44
     riva
    1.42
     magis
    1.41
     saar
    1.36
     milano
    1.36
    Activations Density 0.283%

    No Known Activations