© 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. 6983
    Prev
    Next
    INDEX
    Explanations

    information related to assembly processes, requirements, and equipment

    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
    156
    +0.14
    0.8%
    50
    +0.14
    0.8%
    1757
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.14
    0.03
    1865
    +0.14
    0.02
    537
    +0.11
    0.02
    Negative Logits
    <bos>
    -3.02
    ⓧ
    -0.99
    /***
    
    -0.85
    <?
    -0.81
     defray
    -0.69
    
    
    -0.67
    /**
    -0.67
    /*
    -0.66
    /*!
    
    -0.61
    HasIndex
    -0.59
    POSITIVE LOGITS
    sembly
    1.35
     Assembly
    1.21
     assembly
    1.20
    Assembly
    1.17
     nuoc
    1.15
     ASSEMBLY
    1.14
     thuy
    1.14
     mef
    1.11
     umo
    1.10
     dises
    1.10
    Activations Density 0.103%

    No Known Activations