© 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. 705
    Prev
    Next
    INDEX
    Explanations

    mentions of chemical compounds and elements

    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
    +0.24
    2.1%
    382
    +0.15
    1.3%
    2019
    +0.10
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.24
    0.43
    1535
    +0.15
    0.02
    2034
    +0.10
    0.33
    Negative Logits
    <bos>
    -2.51
    ⓧ
    -1.35
    
    
    -1.17
    <?
    -1.15
    /**
    -1.14
    ///**
    -0.97
    /*
    -0.97
    /***
    
    -0.95
    <?
    
    -0.91
     springfox
    -0.90
    POSITIVE LOGITS
     maneu
    1.30
     accla
    1.27
     affor
    1.20
     Juf
    1.15
     impra
    1.13
     véhic
    1.10
     Keny
    1.10
     fortn
    1.09
     maroc
    1.07
     increa
    1.07
    Activations Density 3.766%

    No Known Activations