Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 738
    Prev
    Next
    INDEX
    Explanations

    concepts regarding widespread issues or concerns, particularly those that are systematic or systemic in nature

    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
    +0.21
    0.9%
    900
    +0.11
    0.5%
    1810
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1810
    +0.21
    0.02
    900
    +0.11
    0.02
    198
    +0.11
    0.02
    Negative Logits
    <bos>
    -3.02
     try
    -0.67
    /***
    
    -0.66
     só
    -0.65
     manage
    -0.64
     deliver
    -0.64
    rungsseite
    -0.63
    HasColumnName
    -0.63
    Subjects
    -0.63
     teach
    -0.62
    POSITIVE LOGITS
     ftu
    1.77
     napoli
    1.76
     hcm
    1.68
     fta
    1.68
     lele
    1.61
     ecru
    1.61
     kyo
    1.60
     aen
    1.60
     jaya
    1.59
     squa
    1.58
    Activations Density 0.101%

    No Known Activations