© 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. 4388
    Prev
    Next
    INDEX
    Explanations

    occurrences of mathematical notation or function representations

    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
    +0.23
    0.9%
    678
    +0.11
    0.4%
    1978
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1505
    +0.23
    0.05
    605
    +0.11
    0.02
    24
    +0.09
    0.04
    Negative Logits
    <bos>
    -1.98
    ⓧ
    -1.15
    
    -1.10
    /**
    -0.95
    <?
    -0.86
     hairc
    -0.77
     springfox
    -0.72
     caucasian
    -0.68
     caress
    -0.68
     cushi
    -0.67
    POSITIVE LOGITS
     ananas
    0.95
     bandung
    0.93
     jati
    0.93
     cæ
    0.91
     lemp
    0.90
     pedas
    0.87
     madu
    0.87
     keramik
    0.86
     lele
    0.86
     jawa
    0.86
    Activations Density 0.227%

    No Known Activations