© 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. 3041
    Prev
    Next
    INDEX
    Explanations

    mentions of diplomatic discussions or agreements between countries

    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
    +0.26
    1.0%
    344
    +0.10
    0.4%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.26
    0.07
    1048
    +0.10
    0.05
    1823
    +0.09
    0.05
    Negative Logits
    <bos>
    -1.72
     hairc
    -1.10
     overcrow
    -1.09
     intersper
    -1.04
     swarovski
    -1.03
    ⓧ
    -1.00
     tupperware
    -0.99
     amigurumi
    -0.93
     cushi
    -0.91
     crê
    -0.89
    POSITIVE LOGITS
     keramik
    0.73
     kemer
    0.69
     ruinas
    0.68
     kapsul
    0.67
     ekster
    0.66
     blanda
    0.65
     soulign
    0.65
     elektronik
    0.63
     Keny
    0.63
     spécialement
    0.62
    Activations Density 0.661%

    No Known Activations