© 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. 6421
    Prev
    Next
    INDEX
    Explanations

    instances of the word "example" followed by a number and potentially a comma and additional number

    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
    +0.24
    1.1%
    1127
    +0.10
    0.5%
    1637
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1637
    +0.24
    0.03
    1127
    +0.10
    0.03
    361
    +0.09
    0.03
    Negative Logits
    <bos>
    -3.00
    /***
    -0.99
    ⓧ
    -0.89
    ///**
    -0.78
    #![
    -0.72
    <?
    -0.71
    /*!
    -0.69
    <?
    -0.68
    //});
    -0.67
    Более
    -0.63
    POSITIVE LOGITS
     quoc
    1.12
     ftu
    1.11
     maneu
    1.11
     kyo
    1.09
     umo
    1.06
     fta
    1.06
     bandung
    1.06
     aveug
    1.05
     guarante
    1.04
     véhic
    1.04
    Activations Density 0.121%

    No Known Activations