© 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. 5003
    Prev
    Next
    INDEX
    Explanations

    expressions of audience engagement and invitations

    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
    +0.39
    1.5%
    227
    +0.17
    0.7%
    381
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.39
    0.06
    1539
    +0.17
    0.04
    1403
    +0.13
    0.01
    Negative Logits
    <bos>
    -1.92
     INSEE
    -0.79
     onStop
    -0.79
    MatButtonModule
    -0.77
    LayoutConstraint
    -0.76
    CardModule
    -0.74
    ButtonModule
    -0.73
    Nascimento
    -0.73
    IconModule
    -0.73
     SIMBAD
    -0.72
    POSITIVE LOGITS
     reluct
    2.80
     accla
    2.79
     maneu
    2.74
     impra
    2.66
     affor
    2.63
     increa
    2.56
     disagre
    2.49
     shenan
    2.47
     depic
    2.46
     disreg
    2.46
    Activations Density 0.831%

    No Known Activations