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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5612
    Prev
    Next
    INDEX
    Explanations

    reviews or comments left by customers on products or services

    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
    +0.23
    1.2%
    1416
    +0.12
    0.6%
    1265
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1416
    +0.23
    0.07
    1398
    +0.12
    0.06
    1047
    +0.11
    0.05
    Negative Logits
    <bos>
    -3.18
    ⓧ
    -1.65
    <?
    -1.24
    /**
    -1.17
    
    
    -1.04
    /***
    
    -0.96
    /*
    -0.89
    #![
    -0.85
    <?
    
    -0.81
    Примеча
    -0.75
    POSITIVE LOGITS
     lele
    1.28
     saar
    1.21
     meis
    1.15
     uhr
    1.13
     maroc
    1.04
     alpes
    1.04
     ohr
    1.01
     ananas
    1.01
     lemp
    0.98
     vinci
    0.98
    Activations Density 0.161%

    No Known Activations