© 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. 1884
    Prev
    Next
    INDEX
    Explanations

    medical terms related to gastrointestinal health, veterinary diagnostics, and surgical procedures

    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
    509
    +0.15
    0.5%
    1906
    +0.09
    0.2%
    876
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.15
    0.04
    1906
    +0.09
    0.05
    509
    +0.08
    0.04
    Negative Logits
     endeavored
    -0.80
     endeavoured
    -0.74
    /*
    -0.70
    ⓧ
    -0.67
     strove
    -0.65
     chanced
    -0.65
    
    -0.65
     fulf
    -0.62
     reaff
    -0.62
    /**
    -0.61
    POSITIVE LOGITS
     affitto
    1.17
     phosphoric
    1.12
    celona
    1.11
     broderie
    1.10
     rectum
    1.09
     sarili
    1.09
     uchiha
    1.06
     urethra
    1.06
     aliphatic
    1.05
     ecru
    1.04
    Activations Density 0.219%

    No Known Activations