© 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. 2298
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values or important numerical data in the text

    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
    +0.19
    0.8%
    2019
    +0.15
    0.7%
    1967
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.19
    0.08
    871
    +0.15
    0.08
    1905
    +0.15
    0.07
    Negative Logits
    <bos>
    -2.55
    ⓧ
    -0.88
    /**
    -0.83
     simplifié
    -0.75
     esternos
    -0.73
     تانيه
    -0.70
    /*
    -0.69
    +:+
    -0.68
     nadzie
    -0.67
     Walkover
    -0.66
    POSITIVE LOGITS
     Juf
    1.60
     silikon
    1.54
     hcm
    1.54
     bandung
    1.52
     alberto
    1.50
     ricardo
    1.48
     keramik
    1.48
     javier
    1.46
     Minang
    1.45
     sappi
    1.45
    Activations Density 0.381%

    No Known Activations