© 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. 7452
    Prev
    Next
    INDEX
    Explanations

    relevant information about political events or significant accomplishments

    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
    1385
    +0.12
    0.4%
    1870
    +0.12
    0.3%
    1705
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.12
    0.05
    86
    +0.12
    0.03
    1036
    +0.11
    0.02
    Negative Logits
     erk
    -0.69
     éter
    -0.60
     :—
    -0.59
     verily
    -0.56
     ofre
    -0.54
     shewn
    -0.54
     kupa
    -0.54
     oreille
    -0.54
     Ferdin
    -0.54
     withal
    -0.54
    POSITIVE LOGITS
     Compañ
    0.72
     Mejía
    0.66
     Áng
    0.65
     Darío
    0.62
     Apare
    0.62
     Redacción
    0.61
     Cár
    0.60
     Asunción
    0.58
     churrasco
    0.58
    Caratter
    0.57
    Activations Density 0.154%

    No Known Activations