© 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. 3790
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "Cabala" or Kabbalistic themes

    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
    +0.15
    0.9%
    341
    +0.15
    0.9%
    1047
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.15
    0.02
    1047
    +0.15
    0.02
    994
    +0.12
    0.01
    Negative Logits
    <bos>
    -1.90
     intersper
    -0.99
     endow
    -0.88
     strove
    -0.79
     interposed
    -0.78
     overcrow
    -0.77
     endeavored
    -0.76
     encomp
    -0.75
     disbur
    -0.74
     endeavoured
    -0.73
    POSITIVE LOGITS
     Cab
    1.60
    Cab
    1.46
     cab
    1.44
    cab
    1.17
     cabs
    1.17
     CAB
    1.17
    CAB
    1.04
     Kab
    1.02
    Cabin
    0.98
     kab
    0.98
    Activations Density 0.043%

    No Known Activations