© 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. 2572
    Prev
    Next
    INDEX
    Explanations

    text related to product descriptions and specifications

    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.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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1385
    +0.18
    0.6%
    876
    +0.07
    0.2%
    823
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.18
    0.07
    823
    +0.07
    0.05
    2014
    +0.06
    0.03
    Negative Logits
     kontinu
    -0.92
     deklar
    -0.81
     kriminal
    -0.77
     konkre
    -0.76
     Gouver
    -0.76
     fash
    -0.76
     chande
    -0.74
     kompati
    -0.74
     indik
    -0.73
     induk
    -0.71
    POSITIVE LOGITS
     nylon
    1.43
     polyester
    1.33
     silk
    1.28
     velvet
    1.26
     silicone
    1.18
     suede
    1.13
     Nylon
    1.09
     satin
    1.08
     spandex
    1.07
     Polyester
    1.06
    Activations Density 0.236%

    No Known Activations