© 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. 4824
    Prev
    Next
    INDEX
    Explanations

    phrases containing contractions and informal speech

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.20
    0.9%
    2019
    +0.14
    0.6%
    1224
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.20
    0.10
    1224
    +0.14
    0.08
    1108
    +0.12
    0.08
    Negative Logits
    <bos>
    -3.37
    ⓧ
    -1.68
    <?
    -1.50
     intersper
    -1.49
     hairc
    -1.48
    /**
    -1.41
     swarovski
    -1.39
    
    -1.37
     Messieurs
    -1.30
     hentai
    -1.29
    POSITIVE LOGITS
    ’
    0.78
    '
    0.73
    mathrm
    0.72
     demokra
    0.71
    ()")
    0.66
    2
    0.65
    A
    0.63
    ']
    0.63
    S
    0.62
    1
    0.62
    Activations Density 0.426%

    No Known Activations