© 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. 3536
    Prev
    Next
    INDEX
    Explanations

    terms related to the judicial system and legal proceedings

    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
    +0.21
    1.1%
    1870
    +0.15
    0.8%
    1472
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.21
    0.02
    1472
    +0.15
    0.02
    1870
    +0.13
    0.01
    Negative Logits
    <bos>
    -2.81
     disbur
    -0.62
    add
    -0.61
     defray
    -0.58
     consolidate
    -0.58
    by
    -0.57
    append
    -0.57
    format
    -0.57
    cont
    -0.56
    export
    -0.56
    POSITIVE LOGITS
     applau
    1.16
    fordable
    1.15
     napoli
    1.11
     valencia
    1.10
     excru
    1.09
     prado
    1.09
     Minang
    1.08
     bandung
    1.08
     uncin
    1.08
     pernic
    1.08
    Activations Density 0.047%

    No Known Activations