© 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. 1102
    Prev
    Next
    INDEX
    Explanations

    sophisticated features in various 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
    1757
    +0.08
    0.2%
    625
    +0.07
    0.2%
    1446
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1446
    +0.08
    0.02
    1229
    +0.07
    0.02
    1366
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.81
    sendRedirect
    -0.68
     plan
    -0.67
    MLLoader
    -0.66
     em
    -0.65
    |()
    -0.63
    <>();
    -0.63
    <table>
    -0.63
    快
    -0.63
    left
    -0.62
    POSITIVE LOGITS
     sophistic
    2.83
     sophistication
    2.33
     sophisticated
    2.22
     maneu
    2.08
     indestru
    2.06
     increa
    2.04
     milf
    2.01
    soph
    1.98
     ?...
    1.97
     🤣🤣
    1.96
    Activations Density 0.215%

    No Known Activations