© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3741
    Prev
    Next
    INDEX
    Explanations

    terms related to bugs and issues in software development

    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
    50
    +0.20
    1.1%
    1350
    +0.12
    0.7%
    68
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1387
    +0.20
    0.01
    188
    +0.12
    0.01
    1350
    +0.10
    0.01
    Negative Logits
    <bos>
    -2.57
    /***
    -0.73
    Autoritní
    -0.66
    <tfoot>
    -0.61
    displayquote
    -0.60
    glPopMatrix
    -0.60
    else
    -0.59
    <
    -0.58
    المكان
    -0.58
    glPushMatrix
    -0.57
    POSITIVE LOGITS
     bug
    1.26
     pymysql
    1.23
     Bug
    1.21
     bugs
    1.20
     Minang
    1.15
     Bugs
    1.10
    Bug
    1.10
     saar
    1.07
     Cæsar
    1.07
     mahd
    1.06
    Activations Density 0.030%

    No Known Activations