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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2534
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to locations or businesses

    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
    1120
    +0.09
    0.3%
    1705
    +0.08
    0.2%
    283
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.09
    0.08
    1343
    +0.08
    0.12
    304
    +0.07
    0.06
    Negative Logits
                      
    -1.13
                    
    -1.12
                   
    -1.11
               
    -1.10
                            
    -1.10
                  
    -1.09
                                
    -1.09
                
    -1.09
                               
    -1.09
                       
    -1.09
    POSITIVE LOGITS
     increa
    4.34
     maneu
    4.22
     affor
    4.21
     effe
    4.19
     secon
    4.15
     depic
    4.14
     guarante
    4.12
     wherea
    4.12
     squa
    4.10
     fta
    4.09
    Activations Density 1.274%

    No Known Activations