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. 9232
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical structures or instructions

    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
    +0.21
    1.2%
    732
    +0.10
    0.6%
    1437
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    732
    +0.21
    0.05
    1451
    +0.10
    0.05
    1437
    +0.10
    0.05
    Negative Logits
    <bos>
    -3.49
    },[])
    -0.79
    ⓧ
    -0.75
    
    
    -0.73
    /**
    -0.73
     promote
    -0.71
        
    -0.71
    /*!
    
    -0.70
     get
    -0.70
    //{
    
    -0.70
    POSITIVE LOGITS
     affor
    1.95
     maneu
    1.91
     stockholm
    1.87
     unden
    1.85
     increa
    1.83
     Juf
    1.81
     Augu
    1.81
     fta
    1.76
     accla
    1.76
     reluct
    1.76
    Activations Density 0.157%

    No Known Activations