© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 330
    Prev
    Next
    INDEX
    Explanations

    references to mathematical formulas and algorithms related to optimization or reinforcement learning

    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
    +0.17
    0.7%
    876
    +0.14
    0.6%
    1699
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.17
    0.01
    1699
    +0.14
    0.08
    278
    +0.13
    0.06
    Negative Logits
    <bos>
    -2.28
    ⓧ
    -1.24
    
    -1.07
    /**
    -1.00
    <?
    -0.92
    Fordítás
    -0.91
    /*
    -0.86
    Detalhes
    -0.85
    Neste
    -0.82
    Enllaços
    -0.81
    POSITIVE LOGITS
     wien
    2.87
     bordeaux
    2.63
     fluo
    2.60
     ?...
    2.60
     stockholm
    2.54
     suspic
    2.52
     emphat
    2.52
     napoli
    2.51
     !...
    2.48
     franz
    2.48
    Activations Density 0.376%

    No Known Activations