© 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. 5048
    Prev
    Next
    INDEX
    Explanations

    references to the character "Dodger" or related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    1573
    +0.14
    0.8%
    1052
    +0.14
    0.8%
    1392
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.14
    0.03
    1805
    +0.14
    0.02
    1573
    +0.13
    0.02
    Negative Logits
    <bos>
    -1.21
    /**
    -0.68
     كومونز
    -0.65
     صوتيه
    -0.62
    ężczy
    -0.58
    ItemLayout
    -0.55
    archiviato
    -0.54
    ContentAlignment
    -0.54
    ensement
    -0.54
    
    -0.54
    POSITIVE LOGITS
     Dod
    1.45
    Dod
    1.35
    dod
    1.15
     dod
    1.11
     maksi
    1.03
     Dodgers
    1.01
     saar
    0.99
    DOD
    0.94
     kram
    0.92
     DOD
    0.91
    Activations Density 0.156%

    No Known Activations