© 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. 3236
    Prev
    Next
    INDEX
    Explanations

    terms related to theft and robbery

    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
    +0.22
    0.9%
    331
    +0.10
    0.4%
    1557
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1437
    +0.22
    0.02
    204
    +0.10
    0.02
    1622
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.05
     disbur
    -0.68
     intersper
    -0.66
    /***
    -0.65
     incarcer
    -0.64
     voleva
    -0.64
    
    -0.63
     farà
    -0.61
     defray
    -0.60
     intende
    -0.59
    POSITIVE LOGITS
     robbery
    0.94
     robberies
    0.88
     Robbery
    0.81
     robbers
    0.74
     robbing
    0.69
     theft
    0.68
     Minang
    0.68
     Bekasi
    0.65
     jawa
    0.64
     Buah
    0.63
    Activations Density 0.110%

    No Known Activations