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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 677
    Prev
    Next
    INDEX
    Explanations

    statistics related to percentages and demographic data

    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
    +0.23
    0.8%
    1343
    +0.15
    0.5%
    1473
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.23
    0.07
    792
    +0.15
    0.04
    1570
    +0.09
    0.05
    Negative Logits
    <bos>
    -3.02
    Autoritní
    -0.95
     intersper
    -0.77
     encomp
    -0.75
    ⓧ
    -0.71
    تقاوى
    -0.71
    Personendaten
    -0.69
    EndGlobalSection
    -0.62
    /***
    
    -0.61
    /*++
    -0.60
    POSITIVE LOGITS
     nôtre
    0.68
     kristal
    0.66
     kug
    0.66
     karton
    0.66
     Jambi
    0.63
     uhr
    0.63
     karte
    0.62
     moza
    0.62
     kado
    0.61
    ditto
    0.60
    Activations Density 0.463%

    No Known Activations