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. 10-RES-JB
    6. 6721
    Prev
    Next
    INDEX
    Explanations

    affirmative expressions signifying agreement or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.26
    0.9%
    314
    +0.09
    0.3%
    382
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    595
    +0.26
    0.03
    1473
    +0.09
    0.03
    1419
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.48
    /**
    -0.82
    <?
    -0.77
    /***
    
    -0.73
    ⓧ
    -0.67
    
    
    -0.64
    <?
    
    -0.63
    /*
    -0.63
    [?]
    -0.63
    /**
    
    
    -0.60
    POSITIVE LOGITS
     Minang
    1.09
     bandung
    1.07
     Muhamma
    1.05
     jawa
    1.05
     Jambi
    1.03
     Palembang
    1.01
     Hitam
    0.96
     Juf
    0.93
     pollut
    0.91
     Karang
    0.89
    Activations Density 0.125%

    No Known Activations