© 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. 3506
    Prev
    Next
    INDEX
    Explanations

    names of people and locations, as well as details about events and organizations

    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
    +0.29
    1.3%
    2019
    +0.13
    0.6%
    1741
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.29
    0.08
    1265
    +0.13
    0.07
    16
    +0.08
    0.07
    Negative Logits
    <bos>
    -2.40
    makeText
    -0.71
    //////////////
    -0.68
    
    -0.64
     tiks
    -0.63
    ///////////////
    -0.63
    /////////////
    -0.62
    ynb
    -0.61
    contentLoaded
    -0.61
     duomen
    -0.61
    POSITIVE LOGITS
     affor
    1.29
     increa
    1.27
     véhic
    1.21
     lamborghini
    1.20
     uninten
    1.16
     Juf
    1.15
     maneu
    1.15
     inev
    1.13
     peppa
    1.10
     guarante
    1.09
    Activations Density 0.930%

    No Known Activations