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. 678
    Prev
    Next
    INDEX
    Explanations

    instances of the word "extend" and its variations

    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
    +0.25
    1.4%
    1896
    +0.12
    0.6%
    405
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1763
    +0.25
    0.02
    240
    +0.12
    0.02
    405
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.81
    /***
    
    -0.79
    ///**
    -0.70
    ⓧ
    -0.69
    /**
    -0.63
     sau
    -0.62
     Administrativna
    -0.62
     plate
    -0.61
    //{
    
    -0.61
    memoized
    -0.60
    POSITIVE LOGITS
     fta
    1.60
     thut
    1.49
     aen
    1.46
     maneu
    1.45
     fup
    1.45
     ftu
    1.43
     lele
    1.41
     wien
    1.39
     fte
    1.38
     bandung
    1.37
    Activations Density 0.038%

    No Known Activations