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

    Neuronpedia

    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. 159
    Prev
    Next
    INDEX
    Explanations

    quantifiable time markers and the act of discovering or reaching for something

    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
    +0.31
    1.1%
    690
    +0.10
    0.3%
    1013
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1379
    +0.31
    0.04
    1406
    +0.10
    0.03
    402
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.50
    Autoritní
    -0.61
    <!--
    -0.58
    +#+#
    -0.56
    <>
    -0.52
    principalTable
    -0.51
    //@
    -0.51
     AssemblyTitle
    -0.50
     cristian
    -0.49
     Roskov
    -0.49
    POSITIVE LOGITS
     Minang
    0.98
     jawa
    0.96
     laft
    0.94
     aen
    0.93
     thut
    0.90
     lele
    0.89
     jaya
    0.88
     perfon
    0.87
     finally
    0.87
     nikah
    0.86
    Activations Density 0.430%

    No Known Activations