© 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. 4493
    Prev
    Next
    INDEX
    Explanations

    numerical code terms with the number 8

    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
    1937
    +0.15
    0.6%
    172
    +0.13
    0.5%
    1334
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.15
    0.05
    172
    +0.13
    0.03
    765
    +0.12
    0.03
    Negative Logits
     Dés
    -0.80
     Mère
    -0.78
     Sén
    -0.70
     Meilleur
    -0.69
     seigneur
    -0.68
     chevalier
    -0.67
     Membre
    -0.66
     Septembre
    -0.64
     Père
    -0.61
     Rivière
    -0.60
    POSITIVE LOGITS
    cou
    0.98
    Cou
    0.94
    Tou
    0.93
     Cou
    0.93
     COU
    0.93
     cou
    0.92
     Tou
    0.92
    Sou
    0.91
     Hou
    0.90
     ROU
    0.90
    Activations Density 0.207%

    No Known Activations