© 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. 4974
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or formal titles within the text

    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
    1506
    +0.19
    1.0%
    1363
    +0.17
    0.9%
    161
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.19
    0.05
    1343
    +0.17
    0.04
    227
    +0.15
    0.04
    Negative Logits
    <bos>
    -1.20
    <?
    -0.78
    bardziej
    -0.71
    
    -0.68
     acredita
    -0.64
    /*
    -0.62
     ogóle
    -0.61
     acreditar
    -0.59
    alnız
    -0.59
     móg
    -0.57
    POSITIVE LOGITS
    Permalink
    1.31
     fatica
    0.83
     divertimento
    0.77
     Ruman
    0.73
     gubern
    0.70
    malink
    0.69
     Somal
    0.67
     perpé
    0.67
     vix
    0.67
     bermuda
    0.66
    Activations Density 0.244%

    No Known Activations