© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2141
    Prev
    Next
    INDEX
    Explanations

    references to South Africa and its socio-economic context

    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
    25
    +0.14
    0.6%
    1065
    +0.13
    0.6%
    1562
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.14
    0.03
    1741
    +0.13
    0.00
    1065
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.83
    cline
    -0.71
    WidgetItem
    -0.67
    BarStyle
    -0.66
     nahilalakip
    -0.63
    TagMode
    -0.63
    ValueGenerated
    -0.62
    sync
    -0.62
     iNdEx
    -0.61
     CWE
    -0.60
    POSITIVE LOGITS
     increa
    1.66
     affor
    1.64
     alberto
    1.58
     eduardo
    1.56
     depic
    1.56
     unwarran
    1.54
     nicolas
    1.54
     leonardo
    1.53
     roberto
    1.53
     excru
    1.53
    Activations Density 0.146%

    No Known Activations