© 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. 4974
    Prev
    Next
    INDEX
    Explanations

    information related to personal life events and details like dates, locations, activities, and achievements

    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
    +0.36
    2.6%
    382
    +0.13
    1.0%
    1967
    +0.12
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.36
    0.24
    1896
    +0.13
    0.15
    1034
    +0.12
    0.17
    Negative Logits
    <bos>
    -3.69
    ⓧ
    -0.87
    ///**
    -0.79
    <?
    -0.72
    /**
    -0.71
    //---
    -0.70
    
    -0.69
    //};
    -0.68
    //----
    -0.66
    /***
    -0.64
    POSITIVE LOGITS
     véhic
    1.19
     soulign
    1.10
     valencia
    1.05
     quoique
    1.02
     accla
    1.02
     catég
    1.01
     Keny
    0.98
     considér
    0.97
     épu
    0.96
     réput
    0.96
    Activations Density 1.739%

    No Known Activations