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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 862
    Prev
    Next
    INDEX
    Explanations

    amounts or quantities expressed in numerical values, specifically the word "nearly" followed by a number

    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%
    897
    +0.05
    0.2%
    1575
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    88
    +0.11
    0.04
    1504
    +0.05
    0.04
    1125
    +0.05
    0.04
    Negative Logits
    <bos>
    -1.88
    ⓧ
    -0.93
    /**
    -0.87
    
    -0.83
    ///**
    -0.81
    <?
    -0.79
    /***
    -0.79
    </tbody>
    -0.78
     continue
    -0.74
    <?
    -0.74
    POSITIVE LOGITS
     stockholm
    2.26
     maneu
    2.08
     increa
    2.07
     wien
    2.05
     affor
    2.00
     impra
    1.90
     guarante
    1.90
     squa
    1.89
     effe
    1.88
     lidl
    1.87
    Activations Density 0.066%

    No Known Activations