© 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. 1208
    Prev
    Next
    INDEX
    Explanations

    locations or names related to businesses or events

    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
    1133
    +0.10
    0.3%
    313
    +0.10
    0.3%
    161
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.04
    690
    +0.10
    0.04
    1343
    +0.09
    0.03
    Negative Logits
    
    -0.86
    <?
    -0.85
    /*
    -0.79
    /**
    -0.72
    <?
    -0.62
    #
    -0.58
     aš
    -0.54
    ArgumentParser
    -0.53
    vel
    -0.52
    DispatchToProps
    -0.50
    POSITIVE LOGITS
     Plaza
    1.34
     Prairie
    1.26
    Prairie
    1.15
    Plaza
    1.07
     prairie
    1.04
     plaza
    0.99
     claudia
    0.97
     javier
    0.89
     bayern
    0.89
     Juf
    0.88
    Activations Density 0.254%

    No Known Activations