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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 6426
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.25
    1.3%
    1150
    +0.10
    0.6%
    2034
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.25
    0.05
    1226
    +0.10
    0.05
    1405
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.43
    ⓧ
    -1.27
    /**
    -1.20
    <?
    -1.18
    <?
    -1.05
    
    -1.04
    /***
    -1.00
    /*
    -0.97
    /*!
    -0.79
     rehabilitate
    -0.77
    POSITIVE LOGITS
     Minang
    0.86
     véhic
    0.83
     lele
    0.79
     maroc
    0.79
     catég
    0.77
     bandung
    0.76
     épu
    0.75
     jawa
    0.72
     alté
    0.72
     Pekan
    0.71
    Activations Density 0.127%

    No Known Activations