© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7384
    Prev
    Next
    INDEX
    Explanations

    words related to moral judgment and decision-making, specifically focusing on deficits in personal moral judgment following damage to specific brain regions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    876
    +0.14
    0.4%
    509
    +0.11
    0.4%
    194
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.14
    0.04
    1499
    +0.11
    0.04
    1906
    +0.11
    0.02
    Negative Logits
     costumi
    -0.83
     Alcalde
    -0.82
     Pued
    -0.81
    posób
    -0.78
     Nadie
    -0.75
     Krzysz
    -0.75
     librement
    -0.74
     Venise
    -0.74
     popoli
    -0.74
     Darío
    -0.74
    POSITIVE LOGITS
     aen
    0.65
    gdala
    0.64
     effe
    0.61
     cortex
    0.58
     ille
    0.57
     region
    0.56
     myn
    0.54
     fto
    0.54
     fup
    0.54
     inder
    0.53
    Activations Density 0.159%

    No Known Activations