© 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. 200
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to the reader or audience

    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
    +0.13
    0.5%
    1978
    +0.05
    0.2%
    204
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.13
    0.03
    1566
    +0.05
    0.03
    814
    +0.05
    0.02
    Negative Logits
    <bos>
    -1.56
    ⓧ
    -1.33
    <?
    -1.07
    
    -1.06
    /**
    -0.92
    /***
    -0.84
    /*
    -0.81
    <?
    -0.74
    #
    -0.70
    /**
    -0.66
    POSITIVE LOGITS
     maroc
    1.09
     meis
    1.08
     maneu
    0.96
     disreg
    0.95
     désol
    0.95
     endom
    0.92
     lamborghini
    0.91
     impra
    0.90
     italia
    0.90
     ibiza
    0.90
    Activations Density 0.107%

    No Known Activations