© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 367
    Prev
    Next
    INDEX
    Explanations

    themes related to liberal ideologies and their historical context

    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
    +0.27
    1.1%
    872
    +0.12
    0.5%
    1253
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.27
    0.10
    198
    +0.12
    0.08
    16
    +0.11
    0.09
    Negative Logits
    <bos>
    -3.59
     do
    -0.81
     add
    -0.78
    .
    -0.75
     are
    -0.75
     be
    -0.74
     is
    -0.74
    ,
    -0.73
     for
    -0.73
     in
    -0.72
    POSITIVE LOGITS
     bandung
    1.98
     santiago
    1.89
     napoli
    1.87
     milano
    1.84
     Minang
    1.79
     soggior
    1.72
     palio
    1.71
     ricardo
    1.71
     tramont
    1.70
     alberto
    1.68
    Activations Density 1.110%

    No Known Activations