© 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. 11345
    Prev
    Next
    INDEX
    Explanations

    terms related to historical events or contexts

    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
    1166
    +0.11
    0.3%
    198
    +0.10
    0.3%
    872
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.11
    0.10
    1166
    +0.10
    0.10
    507
    +0.09
    0.06
    Negative Logits
    styleType
    -0.70
    Hentet
    -0.67
     للاسماء
    -0.64
    RegressionTest
    -0.63
    μβρίου
    -0.62
    yntaxException
    -0.58
     متعلقه
    -0.58
    LayoutStyle
    -0.57
    出版年
    -0.56
     initComponents
    -0.56
    POSITIVE LOGITS
     bourg
    0.69
     veau
    0.69
     pavillon
    0.68
     rocher
    0.64
     lapin
    0.63
     puits
    0.61
     jouet
    0.58
     palais
    0.58
     moulin
    0.58
    Comparisons
    0.57
    Activations Density 1.413%

    No Known Activations