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. 652
    Prev
    Next
    INDEX
    Explanations

    forward-looking statements related to business operations and development

    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
    1.0%
    1328
    +0.12
    0.7%
    1376
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.17
    0.03
    1376
    +0.12
    0.03
    2004
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.10
    /***
    
    -0.98
    <?
    -0.86
    /**
    -0.81
    /*!
    
    -0.78
    
    
    -0.77
    /*
    -0.75
    ⓧ
    -0.74
    <?
    
    -0.69
    <!--
    
    -0.65
    POSITIVE LOGITS
     bandung
    1.58
     jaya
    1.51
     lele
    1.48
     Minang
    1.45
     stockholm
    1.44
     saar
    1.39
     affor
    1.38
     jawa
    1.35
     hcm
    1.32
     riva
    1.31
    Activations Density 0.048%

    No Known Activations