© 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. 4905
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically titles and names related to authority figures or leaders

    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
    1343
    +0.17
    0.7%
    453
    +0.11
    0.4%
    1177
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.17
    0.07
    1314
    +0.11
    0.06
    2005
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.28
    ,
    -0.96
     and
    -0.92
     in
    -0.91
     -
    -0.90
     or
    -0.89
     with
    -0.89
     for
    -0.89
     as
    -0.87
    '
    -0.87
    POSITIVE LOGITS
     alkoh
    2.19
     karton
    2.10
     kram
    2.06
     Kategor
    2.03
     silikon
    2.02
     kosme
    2.02
     ananas
    2.00
     keramik
    1.97
     marte
    1.97
     Ottobre
    1.96
    Activations Density 0.250%

    No Known Activations