© 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. 5107
    Prev
    Next
    INDEX
    Explanations

    references to gaming systems, particularly Pathfinder and similar role-playing game elements

    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
    1194
    +0.17
    0.9%
    479
    +0.13
    0.7%
    1350
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1194
    +0.17
    0.04
    227
    +0.13
    0.05
    1351
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.35
    ulaski
    -0.63
    ensacola
    -0.62
     meni
    -0.61
     défaite
    -0.61
     prae
    -0.59
     extraña
    -0.58
     meil
    -0.57
     roh
    -0.57
     servem
    -0.57
    POSITIVE LOGITS
     paradiso
    0.87
     Luglio
    0.86
     Politica
    0.85
     Giugno
    0.82
     tramonto
    0.81
     Chinois
    0.80
     Settembre
    0.79
     pié
    0.77
     Giappone
    0.76
     autunno
    0.76
    Activations Density 0.258%

    No Known Activations