© 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. 10-RES-JB
    11. 1387
    Prev
    Next
    INDEX
    Explanations

    references to financial penalties and income-related policies

    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
    +0.17
    0.7%
    876
    +0.13
    0.5%
    1150
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.17
    0.08
    876
    +0.13
    -0.02
    919
    +0.12
    0.05
    Negative Logits
    <bos>
    -3.00
    
    -1.00
    /**
    -0.99
    ⓧ
    -0.94
    <?
    -0.93
    /*
    -0.83
    lateinit
    -0.78
    /*!
    -0.72
    endwhile
    -0.70
    Obrázky
    -0.70
    POSITIVE LOGITS
     maroc
    1.54
     bandung
    1.53
     Minang
    1.45
     milano
    1.44
     jawa
    1.43
     stockholm
    1.41
     riviera
    1.39
     frankfurt
    1.38
     territo
    1.37
     bangkok
    1.36
    Activations Density 0.707%

    No Known Activations