© 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 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. 6111
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles and reports

    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
    946
    +0.14
    0.4%
    1177
    +0.13
    0.4%
    198
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    946
    +0.14
    0.08
    198
    +0.13
    0.07
    1252
    +0.13
    0.05
    Negative Logits
     bandung
    -1.06
     marte
    -1.03
     chande
    -1.02
     ananas
    -0.99
     jaya
    -0.99
     maroc
    -0.97
     toul
    -0.95
     appétit
    -0.95
     tille
    -0.94
     aquare
    -0.94
    POSITIVE LOGITS
     woman
    0.74
     female
    0.70
     fellow
    0.70
     young
    0.69
     pregnant
    0.69
     senior
    0.68
     male
    0.67
    Dijo
    0.66
     elderly
    0.66
     women
    0.65
    Activations Density 0.557%

    No Known Activations