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

    Neuronpedia

    Jacobian LensNEW
    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. 2550
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical tensions and military conflicts

    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%
    764
    +0.13
    0.5%
    604
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.29
    0.06
    939
    +0.13
    0.08
    1120
    +0.10
    0.00
    Negative Logits
    <bos>
    -2.67
     intersper
    -1.51
     crou
    -1.21
     endow
    -1.14
     overcrow
    -1.12
     rouse
    -1.08
     reconno
    -1.05
     encomp
    -1.00
     vainly
    -1.00
     apprehen
    -1.00
    POSITIVE LOGITS
     Bárbara
    0.98
    GYPT
    0.77
     religione
    0.76
     Valentín
    0.73
     Lucía
    0.72
     marea
    0.71
     alimente
    0.70
     hunde
    0.69
     hiperten
    0.67
     Vergine
    0.67
    Activations Density 1.146%

    No Known Activations