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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 758
    Prev
    Next
    INDEX
    Explanations

    instances of the word "here" in text, potentially in a context of explanation, discussion, or direction

    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
    +0.14
    0.7%
    1671
    +0.06
    0.3%
    331
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1309
    +0.14
    0.07
    1981
    +0.06
    0.07
    1634
    +0.06
    0.07
    Negative Logits
    <bos>
    -1.71
    ⓧ
    -0.95
    /***
    -0.91
    <?
    -0.91
    /*
    -0.88
    /**
    -0.85
    
    -0.84
    ///**
    -0.82
    <?
    -0.79
    })();
    -0.78
    POSITIVE LOGITS
     affor
    2.05
     maneu
    1.98
     impra
    1.85
     scrat
    1.72
     increa
    1.69
     shenan
    1.69
     reluct
    1.68
     accla
    1.68
     strick
    1.66
     wherea
    1.62
    Activations Density 0.099%

    No Known Activations