© 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. 966
    Prev
    Next
    INDEX
    Explanations

    mentions of swords and related terms in historical or fictional contexts

    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
    1044
    +0.08
    0.3%
    1328
    +0.07
    0.3%
    789
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.08
    0.02
    789
    +0.07
    0.02
    1755
    +0.07
    0.01
    Negative Logits
    <bos>
    -1.11
    <?
    -0.87
    ⓧ
    -0.81
    
    -0.80
    /**
    -0.78
    /***
    -0.77
    /*
    -0.61
    /*!
    -0.60
    HasIndex
    -0.60
    <?
    -0.56
    POSITIVE LOGITS
     sword
    2.08
     Sword
    1.89
    sword
    1.79
    Sword
    1.76
     swords
    1.75
     Swords
    1.41
     espada
    1.10
     eduardo
    0.94
     bandung
    0.93
    quarelle
    0.93
    Activations Density 0.078%

    No Known Activations