© 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. 10-RES-JB
    11. 4357
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to solutions or alternatives to problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.27
    1.6%
    1870
    +0.12
    0.7%
    313
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1758
    +0.27
    0.02
    1637
    +0.12
    0.02
    1622
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.91
    /***
    -0.93
    ///**
    -0.80
    ⓧ
    -0.70
     ratify
    -0.68
    //---
    -0.67
     promul
    -0.66
     amass
    -0.66
    /*!
    -0.63
     disbur
    -0.62
    POSITIVE LOGITS
     solution
    1.29
     solutions
    1.25
     Solution
    1.20
    solution
    1.19
     Solutions
    1.08
    Solution
    1.07
    solutions
    1.05
    Solutions
    1.04
     SOLUTION
    1.00
     SOLUTIONS
    0.98
    Activations Density 0.027%

    No Known Activations