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. 934
    Prev
    Next
    INDEX
    Explanations

    references to social connections and relationships

    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
    +0.29
    1.1%
    227
    +0.12
    0.5%
    513
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1252
    +0.29
    0.05
    1235
    +0.12
    0.04
    1786
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.02
    /***
    
    -0.64
     neutralize
    -0.52
     enshr
    -0.49
    ⓧ
    -0.49
     knelt
    -0.48
     minimise
    -0.48
    Agua
    -0.48
     mobilize
    -0.48
     modulate
    -0.47
    POSITIVE LOGITS
     jetta
    1.02
     riva
    1.02
     Minang
    0.99
     Græ
    0.99
     lele
    0.97
     sentra
    0.91
     Palembang
    0.90
     Meksi
    0.89
     brune
    0.89
     croce
    0.89
    Activations Density 0.691%

    No Known Activations