© 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. 3947
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures or positions within the government

    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
    0.6%
    1150
    +0.11
    0.4%
    1870
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    809
    +0.17
    0.06
    227
    +0.11
    0.06
    1001
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.68
    ⓧ
    -0.98
     /**
    -0.94
    /***
    -0.92
     intersper
    -0.89
    
    -0.81
    <?
    -0.78
     endow
    -0.78
     swarovski
    -0.72
    /**
    -0.70
    POSITIVE LOGITS
     kaos
    0.92
     karton
    0.90
     Lombar
    0.90
     silikon
    0.90
     seksi
    0.87
     makro
    0.85
     Amerik
    0.82
     kasa
    0.82
     saar
    0.82
     pank
    0.81
    Activations Density 0.478%

    No Known Activations