Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15309
    Prev
    Next
    INDEX
    Explanations

    differences or distinctions between concepts, objects, or ideas

    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
    +0.17
    1.0%
    1757
    +0.12
    0.7%
    866
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.17
    0.03
    1757
    +0.12
    0.03
    866
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.17
    ⓧ
    -0.99
    
    
    -0.84
    /*
    -0.83
    <?
    -0.82
    /***
    
    -0.80
    /**
    -0.78
    ///**
    -0.73
    /*!
    
    -0.67
    /*++
    -0.65
    POSITIVE LOGITS
     jaya
    1.48
     stockholm
    1.45
     lele
    1.43
     wien
    1.37
     bandung
    1.34
     saar
    1.33
     aen
    1.33
     meis
    1.32
     frankfurt
    1.32
     effe
    1.30
    Activations Density 0.096%

    No Known Activations