© 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. 984
    Prev
    Next
    INDEX
    Explanations

    newspaper article excerpts pertaining to criminal activities and legal proceedings

    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
    +0.19
    0.8%
    1741
    +0.09
    0.4%
    136
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1003
    +0.19
    0.07
    300
    +0.09
    0.06
    173
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.38
    /***
    -0.86
    ⓧ
    -0.85
    /**
    -0.80
    <?
    -0.80
    <?
    -0.71
    
    -0.70
     /**
    -0.68
    //};
    -0.68
    /*
    -0.66
    POSITIVE LOGITS
     Khart
    1.08
     véhic
    1.03
     catég
    0.91
     Varan
    0.90
     déliv
    0.89
     réput
    0.87
     Hez
    0.87
     préc
    0.85
     expéri
    0.82
     récomp
    0.81
    Activations Density 0.242%

    No Known Activations