© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 136
    Prev
    Next
    INDEX
    Explanations

    quotes and direct speech

    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
    +0.18
    1.0%
    2019
    +0.07
    0.4%
    871
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    871
    +0.18
    0.07
    1709
    +0.07
    0.07
    545
    +0.06
    0.07
    Negative Logits
    <bos>
    -1.59
    ⓧ
    -0.97
    <?
    -0.96
    
    
    -0.85
    /**
    -0.83
    /*
    -0.78
     continue
    -0.70
    /*!
    
    -0.69
    <?
    
    -0.67
    /*++
    -0.66
    POSITIVE LOGITS
     maneu
    1.63
     maroc
    1.59
     affor
    1.59
     embodi
    1.56
     stockholm
    1.52
     roberto
    1.49
     ricardo
    1.46
     accla
    1.46
     lidl
    1.45
     jorge
    1.45
    Activations Density 0.280%

    No Known Activations