© 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. 2629
    Prev
    Next
    INDEX
    Explanations

    ingredients and steps in a baking recipe

    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
    554
    +0.08
    0.2%
    1810
    +0.08
    0.2%
    410
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.05
    1120
    +0.08
    0.04
    690
    +0.08
    0.05
    Negative Logits
     paisley
    -0.74
     choker
    -0.73
     valentines
    -0.71
     hairc
    -0.69
     evermore
    -0.67
     loveliness
    -0.66
     turtleneck
    -0.66
     velour
    -0.65
     gaily
    -0.65
     waifu
    -0.65
    POSITIVE LOGITS
    rey
    1.20
    kj
    1.16
     Preheat
    1.14
    Preheat
    1.13
     cyr
    0.97
     Epif
    0.88
     spie
    0.85
     nutr
    0.85
     Gij
    0.83
     Magist
    0.83
    Activations Density 0.302%

    No Known Activations