© 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. 5849
    Prev
    Next
    INDEX
    Explanations

    mentions of statistical data, trends, and analysis on societal or economic issues

    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
    +0.26
    1.0%
    1253
    +0.09
    0.3%
    1499
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1253
    +0.26
    0.04
    327
    +0.09
    0.06
    1726
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.80
    ⓧ
    -0.92
    <?
    -0.86
    
    -0.81
    /***
    -0.78
    /**
    -0.74
    Transkript
    -0.69
    <?
    -0.65
    Transcripción
    -0.63
    ždý
    -0.61
    POSITIVE LOGITS
     Muhamma
    1.03
     seksi
    0.94
     Bekasi
    0.91
     kafe
    0.90
     jati
    0.90
     jawa
    0.89
     taha
    0.88
     Minang
    0.88
     saha
    0.87
     Banjar
    0.87
    Activations Density 0.904%

    No Known Activations