© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 271
    Prev
    Next
    INDEX
    Explanations

    steps and instructions related to cooking or food preparation

    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
    +0.29
    1.2%
    453
    +0.16
    0.7%
    876
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.29
    0.05
    1284
    +0.16
    0.04
    876
    +0.13
    -0.00
    Negative Logits
    <bos>
    -2.18
     solidar
    -0.80
    /***
    
    -0.79
    <?
    
    -0.76
    /**
    -0.75
     meras
    -0.74
    ⓧ
    -0.73
     ideolog
    -0.70
     Irán
    -0.70
    
    
    -0.69
    POSITIVE LOGITS
     impra
    0.95
     increa
    0.95
     embodi
    0.94
     affor
    0.91
     originaire
    0.90
     nephe
    0.87
     uniqu
    0.86
     suscep
    0.84
     maneu
    0.83
     Juf
    0.82
    Activations Density 0.132%

    No Known Activations