© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    - medical terms related to erectile dysfunction and medications. - terms related to resistance to medications, especially fluoroquinolone class. - specific terms such as "levitra," "scribes," and "homeowner" in unique contexts

    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
    1068
    +0.10
    0.3%
    241
    +0.09
    0.3%
    882
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.10
    0.04
    184
    +0.09
    0.02
    690
    +0.09
    0.06
    Negative Logits
     Intere
    -0.99
     sergio
    -0.98
     pixabay
    -0.96
     shenan
    -0.95
     ricardo
    -0.95
     napoli
    -0.95
     roberto
    -0.92
     shutterstock
    -0.92
    Lma
    -0.91
     Wtf
    -0.90
    POSITIVE LOGITS
    olone
    1.09
     chore
    0.99
     levit
    0.85
     fib
    0.81
     homeowner
    0.80
    ien
    0.75
    nsic
    0.73
     homeowners
    0.73
    abestanden
    0.73
     Walkover
    0.71
    Activations Density 0.434%

    No Known Activations