© 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. 226
    Prev
    Next
    INDEX
    Explanations

    text related to paying tribute to individuals or events

    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
    +0.21
    0.8%
    1618
    +0.10
    0.4%
    994
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    947
    +0.21
    0.03
    1618
    +0.10
    0.03
    1953
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.37
    ⓧ
    -0.81
    <?
    -0.80
    /***
    -0.76
    /**
    -0.74
    
    -0.73
    Πηγές
    -0.71
    قایناقلار
    -0.71
    /*
    -0.69
    ValueGeneration
    -0.68
    POSITIVE LOGITS
     maneu
    1.59
     impra
    1.46
     increa
    1.39
     reluct
    1.34
     scrat
    1.26
     strick
    1.25
     disagre
    1.24
     inev
    1.24
     depic
    1.23
     unspeak
    1.20
    Activations Density 0.344%

    No Known Activations