© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 559
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a deep emotional impact or gratefulness

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.13
    0.5%
    50
    +0.09
    0.4%
    406
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    607
    +0.13
    0.04
    446
    +0.09
    0.04
    1446
    +0.06
    0.03
    Negative Logits
    /***
    -0.90
    <bos>
    -0.88
    <?
    -0.83
    <!--
    -0.71
    //};
    -0.66
    ⓧ
    -0.64
    //{
    -0.64
    /*!
    -0.63
    ///**
    -0.62
    //}
    -0.59
    POSITIVE LOGITS
     truly
    1.66
    truly
    1.62
     Truly
    1.50
    Truly
    1.45
     chrysler
    1.43
     lamborghini
    1.26
     isuzu
    1.24
     genuinely
    1.21
     stockholm
    1.20
     chevrolet
    1.19
    Activations Density 0.106%

    No Known Activations