© 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. 991
    Prev
    Next
    INDEX
    Explanations

    mentions of Blu-ray technology

    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
    +0.07
    0.3%
    316
    +0.07
    0.3%
    1272
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.07
    0.04
    257
    +0.07
    0.03
    733
    +0.06
    0.03
    Negative Logits
    <bos>
    -0.99
            
    -0.85
                
    -0.84
        
    -0.83
    	
    -0.82
    enumerate
    -0.82
    public
    -0.80
    addComponent
    -0.80
    //
    -0.80
                    
    -0.79
    POSITIVE LOGITS
     affor
    2.60
     increa
    2.54
     maneu
    2.51
     fta
    2.37
     inev
    2.35
     accla
    2.34
     emphat
    2.28
     guarante
    2.27
     volunte
    2.25
     Intere
    2.25
    Activations Density 0.092%

    No Known Activations