© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3798
    Prev
    Next
    INDEX
    Explanations

    references to the city of Orlando

    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
    1806
    +0.18
    1.0%
    313
    +0.14
    0.8%
    47
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.18
    0.02
    1741
    +0.14
    0.01
    172
    +0.14
    0.01
    Negative Logits
    <bos>
    -1.45
    ⓧ
    -0.68
    vece
    -0.57
    /***
    -0.54
    squareup
    -0.53
     waive
    -0.52
    posób
    -0.51
     intersper
    -0.50
     gratify
    -0.50
    AlterField
    -0.49
    POSITIVE LOGITS
     Orlando
    1.53
    Orlando
    1.42
     orlando
    1.16
     kram
    0.91
     kaos
    0.89
     plak
    0.86
     antik
    0.78
     panik
    0.76
     optik
    0.76
     stik
    0.76
    Activations Density 0.094%

    No Known Activations