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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5732
    Prev
    Next
    INDEX
    Explanations

    information related to organizational leadership and health programs

    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
    +0.31
    2.1%
    2019
    +0.13
    0.9%
    1870
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.31
    0.18
    1892
    +0.13
    0.17
    1265
    +0.11
    0.16
    Negative Logits
    <bos>
    -3.86
    
    -1.10
    ⓧ
    -1.07
    <?
    -1.00
    /**
    -0.96
     kasarigan
    -0.91
     referenties
    -0.89
    <?
    -0.87
     دیکھیے
    -0.81
    /*
    -0.80
    POSITIVE LOGITS
     maneu
    2.00
     increa
    1.96
     affor
    1.85
     impra
    1.80
     guarante
    1.78
     disagre
    1.77
     reluct
    1.76
     inev
    1.75
     scrat
    1.72
     strick
    1.71
    Activations Density 1.932%

    No Known Activations