© 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. 5868
    Prev
    Next
    INDEX
    Explanations

    dates and statistics related to population changes and health trends

    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
    +0.23
    0.9%
    1499
    +0.13
    0.5%
    1967
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.23
    0.11
    1643
    +0.13
    0.09
    1499
    +0.10
    0.09
    Negative Logits
    <bos>
    -3.71
    ⓧ
    -1.15
    /**
    -0.99
    
    -0.98
    <?
    -0.82
    /*++
    -0.79
    /*!
    -0.78
    /***
    -0.78
    <?
    -0.75
    Transkript
    -0.73
    POSITIVE LOGITS
     kaos
    1.17
     seksi
    1.16
     saar
    1.08
     jawa
    1.07
     jati
    1.06
     hcm
    1.04
     kac
    1.01
     optik
    1.00
     jaya
    0.99
     saha
    0.98
    Activations Density 0.666%

    No Known Activations