© 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. 1432
    Prev
    Next
    INDEX
    Explanations

    phrases related to differentiation within groups or categories

    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
    +0.30
    1.3%
    1678
    +0.11
    0.5%
    1984
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1581
    +0.30
    0.03
    1678
    +0.11
    0.03
    406
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.73
     put
    -0.66
     assume
    -0.62
    public
    -0.62
     get
    -0.62
     showed
    -0.61
    sum
    -0.61
     made
    -0.61
     set
    -0.61
    pi
    -0.61
    POSITIVE LOGITS
     Juf
    1.75
     affor
    1.64
     Keny
    1.64
     lele
    1.62
     Minang
    1.55
     disagre
    1.50
     swarovski
    1.50
     increa
    1.50
     reluct
    1.48
     unwarran
    1.46
    Activations Density 0.049%

    No Known Activations