© 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. 1891
    Prev
    Next
    INDEX
    Explanations

    JavaScript or Python code snippets related to web development

    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
    227
    +0.25
    0.8%
    876
    +0.16
    0.5%
    453
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.25
    0.00
    453
    +0.16
    0.03
    1871
    +0.16
    0.03
    Negative Logits
     compared
    -0.68
     might
    -0.66
    AnchorStyles
    -0.66
     may
    -0.66
     during
    -0.65
     isn
    -0.65
     non
    -0.65
     could
    -0.65
    <bos>
    -0.64
    比较
    -0.64
    POSITIVE LOGITS
     ?...
    1.98
     !...
    1.92
     fto
    1.87
     wong
    1.82
     wien
    1.82
     lola
    1.81
     aen
    1.79
     alre
    1.79
     effe
    1.79
     fta
    1.78
    Activations Density 0.089%

    No Known Activations