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. 6-RES-JB
    6. 872
    Prev
    Next
    INDEX
    Explanations

    coding-related terms and mathematical expressions

    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
    +0.23
    1.5%
    82
    +0.14
    0.9%
    32
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.23
    0.02
    82
    +0.14
    0.02
    1387
    +0.13
    0.02
    Negative Logits
    <bos>
    -3.26
    <?
    -1.28
    ⓧ
    -1.26
    
    
    -1.15
    /**
    -1.12
    /*
    -0.91
    <?
    
    -0.71
    Transcripción
    -0.69
    /***
    
    -0.68
    /*++
    -0.67
    POSITIVE LOGITS
     kaos
    0.94
     bandung
    0.93
     seksi
    0.93
     maroc
    0.93
     véhic
    0.91
    "=
    0.88
     kafe
    0.87
     tramont
    0.86
     lele
    0.86
     incess
    0.85
    Activations Density 0.091%

    No Known Activations