© 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. 0-RES-JB
    11. 113
    Prev
    Next
    INDEX
    Explanations

    financial and economic news and information

    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
    +0.19
    1.2%
    82
    +0.08
    0.5%
    2019
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.19
    0.09
    1102
    +0.08
    0.07
    1774
    +0.07
    0.07
    Negative Logits
    <bos>
    -1.98
    ⓧ
    -1.02
    
    -0.90
    /**
    -0.87
    <?
    -0.87
    /***
    -0.85
    <?
    -0.83
    ///**
    -0.83
     springfox
    -0.78
    /*!
    -0.72
    POSITIVE LOGITS
     maneu
    1.20
     affor
    1.15
     véhic
    1.15
     -
    1.07
     impra
    1.04
     -"
    1.03
     soulign
    1.02
     délib
    1.01
     catég
    1.01
     épu
    0.99
    Activations Density 0.211%

    No Known Activations