© 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. 2681
    Prev
    Next
    INDEX
    Explanations

    terms related to automotive industry and technology

    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
    1870
    +0.12
    0.4%
    893
    +0.08
    0.3%
    1385
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.12
    0.05
    1870
    +0.08
    0.01
    1540
    +0.08
    0.02
    Negative Logits
    /**
    -1.04
    <bos>
    -1.03
    ⓧ
    -0.91
    
    -0.84
    /*
    -0.81
    <?
    -0.77
    /*++
    -0.71
     nahilalakip
    -0.69
    <?
    -0.65
    //
    -0.64
    POSITIVE LOGITS
     bandung
    1.59
     napoli
    1.36
     🔥🔥
    1.30
     chèvre
    1.27
     Minang
    1.26
     Février
    1.26
     Souha
    1.24
     bordeaux
    1.24
     🤣🤣
    1.24
     Chapitre
    1.23
    Activations Density 0.203%

    No Known Activations