© 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. 6-RES-JB
    11. 3482
    Prev
    Next
    INDEX
    Explanations

    keywords related to search engines and technology

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    1.1%
    938
    +0.12
    0.7%
    597
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    938
    +0.18
    0.06
    597
    +0.12
    0.05
    559
    +0.11
    0.05
    Negative Logits
    <bos>
    -3.33
    HasColumnType
    -0.73
     AssemblyCompany
    -0.72
            
    -0.71
    else
    -0.69
        
    -0.68
     wireType
    -0.68
              
    -0.66
    起
    -0.65
     Italijani
    -0.65
    POSITIVE LOGITS
     affor
    2.06
     impra
    1.94
     maneu
    1.91
     increa
    1.90
     reluct
    1.89
     scrat
    1.89
     accla
    1.88
     swarovski
    1.85
     bandung
    1.84
     disagre
    1.84
    Activations Density 0.128%

    No Known Activations