© 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. 256
    Prev
    Next
    INDEX
    Explanations

    words that end in 'ing' and 'ed' or phrases related to government, politics, and societal 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
    +0.31
    2.1%
    1967
    +0.23
    1.5%
    1363
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.31
    0.14
    1356
    +0.23
    0.07
    1622
    +0.13
    0.06
    Negative Logits
    <bos>
    -3.23
    <?
    -1.04
    ⓧ
    -1.03
    /**
    -0.98
    
    -0.94
    /*!
    -0.81
    /*
    -0.81
    /***
    -0.80
    <?
    -0.79
    /*++
    -0.71
    POSITIVE LOGITS
     bandung
    1.53
     Minang
    1.46
     jaya
    1.43
     lele
    1.40
     Juf
    1.35
     surabaya
    1.25
     accla
    1.25
     jawa
    1.25
     seksi
    1.23
     Confu
    1.22
    Activations Density 1.446%

    No Known Activations