© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4375
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions that indicate opinions about legislation or economic conditions

    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
    +0.28
    1.2%
    604
    +0.15
    0.6%
    468
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.28
    0.11
    1129
    +0.15
    0.09
    1226
    +0.10
    0.07
    Negative Logits
    <bos>
    -3.32
    ⓧ
    -1.09
     intersper
    -1.06
    /***
    -0.97
     suscep
    -0.95
     /**
    -0.95
     hentai
    -0.93
     endow
    -0.91
     funko
    -0.89
    //*/
    -0.87
    POSITIVE LOGITS
     gubern
    0.93
     kaos
    0.78
     maksi
    0.74
     lemp
    0.71
     Muhamma
    0.71
     panik
    0.70
     hunde
    0.70
     PSOE
    0.69
     cemento
    0.68
     simpel
    0.68
    Activations Density 1.076%

    No Known Activations