© 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. 636
    Prev
    Next
    INDEX
    Explanations

    Biblical citations

    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
    50
    +0.17
    1.1%
    1978
    +0.12
    0.8%
    874
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    874
    +0.17
    0.11
    1978
    +0.12
    0.12
    1624
    +0.09
    0.10
    Negative Logits
    <bos>
    -2.26
    ⓧ
    -1.15
    /**
    -0.93
    
    -0.91
    <?
    -0.82
    /*
    -0.81
    /*++
    -0.77
    ///**
    -0.72
    /***
    -0.71
    /*!
    -0.69
    POSITIVE LOGITS
     affor
    1.77
     maneu
    1.74
     increa
    1.72
     impra
    1.62
     accla
    1.52
     stockholm
    1.51
     disagre
    1.49
     inev
    1.48
     embodi
    1.47
     suscep
    1.46
    Activations Density 0.339%

    No Known Activations