© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1950
    Prev
    Next
    INDEX
    Explanations

    terms related to groups and organizations, particularly in a social or political context

    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
    +0.26
    0.9%
    227
    +0.12
    0.4%
    1978
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.26
    0.09
    1414
    +0.12
    0.08
    2034
    +0.09
    0.08
    Negative Logits
    <bos>
    -2.54
    ///**
    -0.77
    heritance
    -0.66
     dico
    -0.65
    habited
    -0.59
     ordina
    -0.59
     dras
    -0.58
    queryInterface
    -0.54
    ostante
    -0.54
    <?
    
    -0.54
    POSITIVE LOGITS
    SBATCH
    0.73
     shippuden
    0.72
     uchiha
    0.72
     kebaya
    0.71
     actionTypes
    0.70
     hilux
    0.67
     ayaa
    0.66
     "$@"
    0.66
     AppBundle
    0.65
     insensible
    0.65
    Activations Density 0.747%

    No Known Activations