Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6784
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "among" followed by references to other related topics or items

    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%
    1052
    +0.11
    0.4%
    486
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.23
    0.02
    645
    +0.11
    0.02
    1052
    +0.10
    0.02
    Negative Logits
    <bos>
    -1.72
    ValueGenerated
    -0.70
    ⓧ
    -0.60
     AssemblyProduct
    -0.59
    HasColumnType
    -0.58
    /***
    
    -0.57
    /**
    
    
    -0.56
     defend
    -0.56
    <!--
    
    -0.56
    fromnode
    -0.55
    POSITIVE LOGITS
     Minang
    1.19
     Palembang
    1.18
     maroc
    1.18
     bandung
    1.12
     jaya
    1.11
     Banjar
    1.10
     impra
    1.06
     Banten
    1.06
     Karang
    1.05
     maneu
    1.04
    Activations Density 0.061%

    No Known Activations