© 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. 633
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms related to names and titles

    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
    1177
    +0.17
    0.7%
    1741
    +0.13
    0.5%
    1978
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.17
    0.04
    80
    +0.13
    0.03
    1978
    +0.12
    0.04
    Negative Logits
    <bos>
    -2.70
    ⓧ
    -1.14
    
    -1.12
    <?
    -0.95
    /**
    -0.94
    #
    -0.77
     initComponents
    -0.77
    /*
    -0.71
    intios
    -0.67
    contentLoaded
    -0.67
    POSITIVE LOGITS
     aen
    1.84
     Juf
    1.72
     thut
    1.72
     dises
    1.71
     nece
    1.67
     emphat
    1.65
     inev
    1.64
     mef
    1.63
     meis
    1.63
     fta
    1.63
    Activations Density 0.175%

    No Known Activations