© 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. 3372
    Prev
    Next
    INDEX
    Explanations

    concepts related to integrity and moral character

    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
    +0.28
    1.1%
    596
    +0.07
    0.3%
    1839
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1135
    +0.28
    0.05
    284
    +0.07
    0.04
    823
    +0.07
    0.05
    Negative Logits
    <bos>
    -1.73
     intersper
    -1.30
     encomp
    -1.28
     benevol
    -1.18
     crou
    -1.12
     reluct
    -1.10
     felicity
    -1.07
     apprehen
    -1.07
     quitted
    -1.07
     disagre
    -1.07
    POSITIVE LOGITS
    MouseAdapter
    0.82
     borsa
    0.69
     bicic
    0.68
     palio
    0.68
     psicologia
    0.67
     lampada
    0.62
     pompa
    0.61
     Cruces
    0.61
     croce
    0.61
     paradiso
    0.60
    Activations Density 1.035%

    No Known Activations