© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 486
    Prev
    Next
    INDEX
    Explanations

    prominent brand names and keywords related to products or events

    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
    +0.28
    1.4%
    1535
    +0.14
    0.7%
    478
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    851
    +0.28
    0.00
    678
    +0.14
    0.00
    282
    +0.11
    0.00
    Negative Logits
    <bos>
    -2.61
    ⓧ
    -1.26
    /**
    -1.18
    
    -1.10
    <?
    -1.07
    /*
    -0.91
    #
    -0.72
    #![
    -0.69
     rehabilitate
    -0.67
    /***
    -0.65
    POSITIVE LOGITS
     seksi
    1.31
     lele
    1.28
     kafe
    1.24
     maroc
    1.14
     kela
    1.14
     jawa
    1.13
     bandung
    1.12
     véhic
    1.12
     Minang
    1.11
     kado
    1.10
    Activations Density 0.001%

    No Known Activations