© 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. 2228
    Prev
    Next
    INDEX
    Explanations

    references to the name "Lex" and its variants

    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
    1604
    +0.13
    0.7%
    1480
    +0.13
    0.7%
    67
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.13
    0.04
    1363
    +0.13
    0.03
    1763
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.75
    ⓧ
    -0.75
    addCriterion
    -0.73
    <?
    -0.66
    França
    -0.65
    mergeFrom
    -0.64
    Autoritní
    -0.64
     "..\..\..\
    -0.63
    GeneratedMessage
    -0.63
    ViewFeatures
    -0.63
    POSITIVE LOGITS
     stratigraph
    1.11
     dott
    0.97
     Telex
    0.96
     trion
    0.94
    nyx
    0.94
     Mox
    0.93
     affari
    0.93
     inext
    0.93
     jax
    0.93
     Ux
    0.92
    Activations Density 0.157%

    No Known Activations