© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2244
    Prev
    Next
    INDEX
    Explanations

    references to specific weightlifting exercises and techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.8%
    876
    +0.11
    0.4%
    736
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.20
    0.04
    736
    +0.11
    0.04
    1331
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.16
    PerformLayout
    -0.80
    //});
    -0.76
    Espèce
    -0.75
    /***
    -0.75
    ///**
    -0.72
    揶
    -0.69
    Geplaatst
    -0.68
    
    -0.66
    ⓧ
    -0.65
    POSITIVE LOGITS
     ecru
    1.14
     swarovski
    1.05
     broderie
    0.98
     velours
    0.96
     hairc
    0.91
     luxuriant
    0.90
     disagre
    0.90
     impra
    0.89
     wattpad
    0.88
     blackish
    0.85
    Activations Density 0.309%

    No Known Activations