© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 241
    Prev
    Next
    INDEX
    Explanations

    medical conditions and terms, especially related to eye health and disorders

    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
    1994
    +0.10
    0.3%
    1921
    +0.08
    0.3%
    410
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1432
    +0.10
    0.03
    1343
    +0.08
    0.03
    1994
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.89
    со
    -0.68
    Identyfik
    -0.65
    ,
    -0.63
    ществует
    -0.62
    าก็
    -0.62
    тельству
    -0.61
     cập
    -0.61
    ⓧ
    -0.60
     avoid
    -0.60
    POSITIVE LOGITS
     IC
    1.96
     Juf
    1.83
     affor
    1.54
     Keny
    1.52
     depic
    1.52
     accla
    1.51
     Confu
    1.50
     Intere
    1.50
     maneu
    1.49
     impra
    1.49
    Activations Density 0.159%

    No Known Activations