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. 6-RES-JB
    6. 9162
    Prev
    Next
    INDEX
    Explanations

    medical terms related to pediatrics, dermatology, internal medicine, and hospital procedures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.17
    0.6%
    1870
    +0.10
    0.4%
    555
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    914
    +0.17
    0.04
    1860
    +0.10
    0.04
    1313
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.00
    ⓧ
    -1.01
    /**
    -0.89
    
    
    -0.80
    <?
    
    -0.75
     AssemblyCompany
    -0.72
    <>
    
    -0.71
    <?
    -0.69
    /*!
    
    -0.67
     intracranial
    -0.65
    POSITIVE LOGITS
     saar
    1.01
     alté
    0.88
     Palembang
    0.86
     Minang
    0.84
     Karakter
    0.83
     Présentation
    0.83
     kaos
    0.82
     Pekan
    0.82
     maksi
    0.81
     Khart
    0.80
    Activations Density 0.216%

    No Known Activations