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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 455
    Prev
    Next
    INDEX
    Explanations

    references to government healthcare programs, specifically Medicaid

    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
    313
    +0.10
    0.3%
    1404
    +0.10
    0.3%
    650
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.10
    0.01
    1363
    +0.10
    0.02
    1120
    +0.10
    0.03
    Negative Logits
    engeance
    -0.73
     pediu
    -0.66
    леге
    -0.59
     declare
    -0.58
    noopener
    -0.58
     voltou
    -0.56
     balance
    -0.56
     esteve
    -0.55
    declare
    -0.55
    cimientos
    -0.55
    POSITIVE LOGITS
     Medicaid
    1.95
    Medica
    1.31
     paradiso
    1.15
     siena
    1.08
     signore
    1.05
     ducato
    1.01
     sonno
    1.01
     trion
    1.00
     tramonto
    0.99
     plong
    0.97
    Activations Density 0.271%

    No Known Activations