© 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. 10-RES-JB
    11. 4813
    Prev
    Next
    INDEX
    Explanations

    terms related to sports team rosters

    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
    421
    +0.14
    0.8%
    1328
    +0.14
    0.8%
    50
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.14
    0.03
    1872
    +0.14
    0.02
    1276
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.76
    ⓧ
    -0.71
    Datuak
    -0.63
     kasarigan
    -0.59
    /**
    -0.57
    writeFieldEnd
    -0.56
    Personendaten
    -0.55
    насе
    -0.55
     AssemblyCompany
    -0.53
    simpleType
    -0.53
    POSITIVE LOGITS
     Roster
    1.00
     ro
    0.96
     swarovski
    0.95
     beverly
    0.91
     roh
    0.90
     RO
    0.88
     roo
    0.87
     Rost
    0.85
    Roster
    0.85
    ro
    0.85
    Activations Density 0.106%

    No Known Activations