© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 1715
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court cases and legal briefs

    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
    1150
    +0.15
    0.5%
    50
    +0.13
    0.5%
    1224
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.15
    0.05
    1363
    +0.13
    0.06
    1224
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.15
    glMatrixMode
    -0.82
    ⓧ
    -0.81
    Autoritní
    -0.80
     protes
    -0.76
    पया
    -0.74
    BeginContext
    -0.71
    })->
    -0.70
     bolí
    -0.69
    tagHelperRunner
    -0.68
    POSITIVE LOGITS
     maneu
    1.57
     impra
    1.51
     unspeak
    1.43
     shenan
    1.42
     reluct
    1.39
     apprehen
    1.35
     sophistic
    1.34
     gaily
    1.34
     indescri
    1.29
     increa
    1.28
    Activations Density 0.766%

    No Known Activations