© 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. 2938
    Prev
    Next
    INDEX
    Explanations

    words related to continuation of reading or provided content

    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
    339
    +0.07
    0.2%
    1093
    +0.07
    0.2%
    431
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1393
    +0.07
    0.03
    456
    +0.07
    0.03
    556
    +0.07
    0.03
    Negative Logits
    /**
    -1.01
    /*
    -0.99
    <?
    -0.94
    ⓧ
    -0.88
    
    -0.83
    Forrás
    -0.70
    המ
    -0.69
    },{
    -0.69
    مؤ
    -0.69
    <?
    -0.69
    POSITIVE LOGITS
     increa
    1.99
     maneu
    1.99
     suscep
    1.94
     impra
    1.93
     intermitt
    1.92
     affor
    1.91
     scrat
    1.89
     inappro
    1.83
     reluct
    1.83
     ?...
    1.82
    Activations Density 0.105%

    No Known Activations