© 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. 3084
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and their variations

    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
    +0.32
    1.5%
    1937
    +0.16
    0.7%
    468
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.32
    0.12
    468
    +0.16
    0.05
    1806
    +0.10
    0.07
    Negative Logits
    <bos>
    -3.21
    Autoritní
    -0.77
    //---
    -0.72
    drawSprites
    -0.70
     Référence
    -0.70
    /**
    -0.70
    <?
    -0.70
    octanol
    -0.69
    oa̍t
    -0.68
    Таким
    -0.67
    POSITIVE LOGITS
     fatis
    1.33
     impractica
    1.31
     ecru
    1.27
     unlaw
    1.26
     embodi
    1.25
     perfon
    1.23
     sovere
    1.22
     accla
    1.21
     hoody
    1.19
     hairc
    1.18
    Activations Density 0.700%

    No Known Activations