© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6603
    Prev
    Next
    INDEX
    Explanations

    exclamatory expressions or phrases denoting strong emotions or emphasis

    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
    478
    +0.19
    1.1%
    2034
    +0.14
    0.8%
    50
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.19
    0.03
    2034
    +0.14
    0.03
    1892
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.79
    <?
    
    -0.97
    <?
    -0.94
    /**
    -0.93
    /***
    
    -0.92
    /*!
    
    -0.82
    
    
    -0.79
    /*
    -0.76
    ⓧ
    -0.74
    /*++
    -0.69
    POSITIVE LOGITS
     paradiso
    1.00
     unlaw
    0.90
     véhic
    0.89
     unwarran
    0.86
     embodi
    0.85
     pollut
    0.85
     roul
    0.85
     Pamph
    0.84
     unden
    0.84
     mélang
    0.84
    Activations Density 0.076%

    No Known Activations