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. 404
    Prev
    Next
    INDEX
    Explanations

    information or instructions related to online registration and event submission

    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
    172
    +0.17
    0.9%
    331
    +0.14
    0.8%
    871
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.17
    0.03
    1515
    +0.14
    0.02
    1548
    +0.14
    0.02
    Negative Logits
    <bos>
    -1.34
     NLR
    -0.62
    /*
    -0.59
    /***
    
    -0.57
    /*!
    
    -0.56
     intersper
    -0.56
     /**
    
    -0.54
     simpsons
    -0.53
     endow
    -0.52
    Corne
    -0.51
    POSITIVE LOGITS
     >>
    1.01
    >>
    0.98
    )>>
    0.95
     silikon
    0.82
    (">>
    0.81
     <<
    0.80
     "<<
    0.78
    <<
    0.78
    ">>
    0.75
    )<<
    0.74
    Activations Density 0.393%

    No Known Activations