© 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. 4696
    Prev
    Next
    INDEX
    Explanations

    terms related to capitalizing on opportunities or situations

    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
    +0.17
    0.7%
    690
    +0.13
    0.5%
    1325
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1325
    +0.17
    0.05
    152
    +0.13
    0.06
    1490
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.47
    /***
    -0.87
    //*/
    -0.68
     ideolog
    -0.67
    /*!
    -0.63
    //});
    -0.62
     púb
    -0.56
     pels
    -0.55
     solidar
    -0.55
     perquè
    -0.54
    POSITIVE LOGITS
     chré
    1.03
     paradiso
    0.92
    relenting
    0.91
    alnız
    0.87
    mistak
    0.84
     affari
    0.84
     particolar
    0.84
    wavering
    0.82
     outlander
    0.82
     pymysql
    0.82
    Activations Density 0.484%

    No Known Activations