© 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. 3473
    Prev
    Next
    INDEX
    Explanations

    terms related to the death penalty and its implications

    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
    +0.24
    0.9%
    1806
    +0.11
    0.4%
    1778
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.24
    0.02
    1806
    +0.11
    0.02
    624
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.85
     mergeFrom
    -0.70
    fileprivate
    -0.65
    create
    -0.62
    define
    -0.61
    पया
    -0.61
    glBindBuffer
    -0.61
    mtable
    -0.60
    Kontrola
    -0.60
    left
    -0.60
    POSITIVE LOGITS
     maneu
    1.83
     increa
    1.76
     stockholm
    1.72
     emphat
    1.69
     impra
    1.66
     Juf
    1.64
     excru
    1.64
     affor
    1.63
     scrat
    1.63
     reluct
    1.61
    Activations Density 0.122%

    No Known Activations