Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6752
    Prev
    Next
    INDEX
    Explanations

    dates and news sources

    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
    +0.29
    1.5%
    382
    +0.10
    0.5%
    2019
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1830
    +0.29
    0.08
    692
    +0.10
    0.07
    1466
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.73
    ⓧ
    -1.31
    
    
    -0.99
    <?
    -0.97
    /**
    -0.92
    /*
    -0.83
    <?
    
    -0.81
    /***
    
    -0.78
    Transcripción
    -0.72
    💼
    -0.68
    POSITIVE LOGITS
     maneu
    1.12
     impra
    0.98
     véhic
    0.96
     accla
    0.90
     unspeak
    0.89
     pleins
    0.88
     affor
    0.87
     reluct
    0.82
     increa
    0.82
     indescri
    0.81
    Activations Density 0.143%

    No Known Activations