© 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. 1542
    Prev
    Next
    INDEX
    Explanations

    references to notable or fictional entities, particularly in film and gaming contexts

    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
    1842
    +0.20
    0.8%
    1177
    +0.17
    0.7%
    1577
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1177
    +0.20
    0.03
    283
    +0.17
    0.03
    227
    +0.13
    0.09
    Negative Logits
    <bos>
    -2.17
    <?
    -1.12
    ⓧ
    -1.12
    
    -1.04
    /**
    -0.98
    /*
    -0.85
     are
    -0.77
     may
    -0.76
     at
    -0.76
     get
    -0.76
    POSITIVE LOGITS
     meis
    2.25
     kram
    2.01
     Kategor
    2.00
     Strukt
    1.96
     antik
    1.95
     lele
    1.94
     aen
    1.90
     mef
    1.90
     Traité
    1.87
     karton
    1.87
    Activations Density 0.585%

    No Known Activations