© 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. 60
    Prev
    Next
    INDEX
    Explanations

    references to the concept of justification or normative reasoning

    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
    1896
    +0.11
    0.4%
    50
    +0.11
    0.4%
    1265
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.11
    0.07
    1363
    +0.11
    0.07
    1074
    +0.11
    0.09
    Negative Logits
     Shakspeare
    -1.79
     quitted
    -1.58
     Pamph
    -1.54
     indor
    -1.51
     apprehen
    -1.49
     reluct
    -1.48
     encomp
    -1.45
     unwarran
    -1.43
     pamph
    -1.40
     unlaw
    -1.38
    POSITIVE LOGITS
     חיצוניים
    0.86
     שוליים
    0.75
    appointing
    0.73
    hastly
    0.72
    gruntled
    0.70
    surate
    0.68
    astrous
    0.68
     '+':
    0.68
    ydın
    0.67
     urme
    0.67
    Activations Density 2.200%

    No Known Activations