© 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. 3244
    Prev
    Next
    INDEX
    Explanations

    references to intoxication and impaired driving

    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
    +0.19
    0.8%
    650
    +0.10
    0.4%
    920
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    544
    +0.19
    0.02
    1233
    +0.10
    0.02
    1935
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.46
    HasAnnotation
    -0.69
     NSCoder
    -0.66
    {~
    -0.66
    Autoritní
    -0.64
    com
    -0.63
    ――
    -0.61
    <tbody>
    -0.61
     AssemblyCompany
    -0.60
    cm
    -0.60
    POSITIVE LOGITS
     Minang
    1.48
     Juf
    1.46
     Banjar
    1.41
     Keny
    1.37
     swarovski
    1.35
     beverly
    1.35
     hairc
    1.34
     tucson
    1.31
     impra
    1.31
     murano
    1.29
    Activations Density 0.058%

    No Known Activations