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. 1832
    Prev
    Next
    INDEX
    Explanations

    references to incarceration and its societal impact

    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
    +0.25
    0.9%
    1842
    +0.15
    0.5%
    1177
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1033
    +0.25
    0.07
    1553
    +0.15
    0.07
    1556
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.24
    PerformLayout
    -0.93
    EndInit
    -0.76
    ⓧ
    -0.75
    لينكات
    -0.66
    
    
    -0.65
    Referencie
    -0.63
    Kjelder
    -0.63
    BeginInit
    -0.61
    جغرافيا
    -0.61
    POSITIVE LOGITS
     bandung
    1.16
     Minang
    1.09
     jati
    1.08
     Muhamma
    1.02
     jaya
    1.01
     Karang
    0.99
     Pekan
    0.97
     jawa
    0.96
     grossa
    0.95
     Jambi
    0.94
    Activations Density 0.748%

    No Known Activations