© 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. 4983
    Prev
    Next
    INDEX
    Explanations

    references to pronouns and their associated subjects or objects

    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
    50
    +0.30
    1.2%
    227
    +0.10
    0.4%
    776
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.30
    0.07
    331
    +0.10
    0.07
    381
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.82
    intios
    -0.72
    HasIndex
    -0.69
     Administrativna
    -0.66
    EndGlobalSection
    -0.66
    writeFieldEnd
    -0.66
    AddColumn
    -0.64
    Autoritní
    -0.64
    expandindo
    -0.61
    |};
    -0.61
    POSITIVE LOGITS
     reluct
    1.68
     impra
    1.67
     disagre
    1.60
     accla
    1.60
     affor
    1.59
     shenan
    1.58
     increa
    1.52
     indestru
    1.49
     fortn
    1.49
     impractica
    1.48
    Activations Density 0.504%

    No Known Activations