© 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. 6-RES-JB
    6. 5201
    Prev
    Next
    INDEX
    Explanations

    instructions related to assembling or constructing objects

    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
    1385
    +0.21
    1.0%
    50
    +0.20
    0.9%
    876
    +0.19
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.21
    0.17
    876
    +0.20
    -0.04
    906
    +0.19
    0.00
    Negative Logits
    <bos>
    -3.30
    ⓧ
    -1.13
    <?
    -1.06
    /**
    -1.01
    
    
    -0.97
    /***
    
    -0.91
    <?
    
    -0.87
     robus
    -0.82
    ///**
    -0.81
     unan
    -0.81
    POSITIVE LOGITS
     bytu
    0.83
     maroc
    0.74
     espagnole
    0.72
     jawa
    0.72
    oubted
    0.70
     piese
    0.68
     zipfile
    0.68
     todella
    0.67
     kardashian
    0.67
    isDebug
    0.66
    Activations Density 2.200%

    No Known Activations