© 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. 459
    Prev
    Next
    INDEX
    Explanations

    references to longstanding practices or customs passed down over time

    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
    +0.08
    0.3%
    270
    +0.07
    0.3%
    492
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.08
    0.03
    155
    +0.07
    0.03
    1727
    +0.06
    0.02
    Negative Logits
    <bos>
    -1.21
    ⓧ
    -0.81
    /**
    -0.78
    
    -0.76
    <?
    -0.72
    <?
    -0.70
     rehabilitate
    -0.66
    /***
    -0.61
    displayquote
    -0.60
    public
    -0.60
    POSITIVE LOGITS
     tradition
    2.19
    tradition
    2.01
     traditions
    1.98
     Tradition
    1.97
    Tradition
    1.85
     Traditions
    1.80
     tradic
    1.51
     tradizione
    1.51
     tradição
    1.39
     tradición
    1.38
    Activations Density 0.121%

    No Known Activations