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. 1054
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Game" and its variations, indicating a focus on sports or competitive events

    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
    +0.18
    1.0%
    805
    +0.11
    0.6%
    1124
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.18
    0.03
    67
    +0.11
    0.02
    1909
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.84
    /**
    -0.82
    
    
    -0.78
    /*
    -0.77
    <?
    -0.72
    ⓧ
    -0.68
    ConverterFactory
    -0.64
    /*++
    -0.63
     reached
    -0.62
    #![
    -0.59
    POSITIVE LOGITS
     maksi
    1.73
     silikon
    1.59
     Meksi
    1.58
     keramik
    1.52
     seksi
    1.47
     antik
    1.46
     saar
    1.45
     Strukt
    1.44
     mikrofon
    1.41
     karton
    1.40
    Activations Density 0.045%

    No Known Activations