© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 594
    Prev
    Next
    INDEX
    Explanations

    information related to taxes and financial transactions

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.11
    0.5%
    67
    +0.05
    0.2%
    1310
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1495
    +0.11
    0.06
    601
    +0.05
    0.04
    1310
    +0.05
    0.04
    Negative Logits
    <bos>
    -1.57
    /**
    -0.99
    ⓧ
    -0.95
    
    -0.92
    /*
    -0.89
    <?
    -0.80
    /***
    -0.71
    <?
    -0.67
     also
    -0.66
     eliminate
    -0.65
    POSITIVE LOGITS
     tax
    1.79
     Tax
    1.77
    Tax
    1.61
     TAX
    1.60
     Juf
    1.51
     stockholm
    1.48
    tax
    1.47
     catég
    1.44
     véhic
    1.42
     wien
    1.41
    Activations Density 0.156%

    No Known Activations