© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2899
    Prev
    Next
    INDEX
    Explanations

    details related to incidents and reports involving damage or accidents

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.25
    3.6%
    382
    +0.15
    2.2%
    2019
    +0.10
    1.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.25
    0.50
    1535
    +0.15
    0.03
    2034
    +0.10
    0.38
    Negative Logits
    <bos>
    -2.50
    ⓧ
    -1.50
    /**
    -1.38
    
    -1.38
    <?
    -1.34
    /***
    -1.13
    /*
    -1.11
    <?
    -1.08
    ///**
    -1.04
     springfox
    -0.92
    POSITIVE LOGITS
     véhic
    0.91
     maroc
    0.90
     catég
    0.84
     maneu
    0.84
     épu
    0.83
     expériment
    0.82
     marea
    0.80
     habile
    0.80
     délib
    0.79
     accla
    0.78
    Activations Density 4.350%

    No Known Activations