© 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. 6075
    Prev
    Next
    INDEX
    Explanations

    code snippets related to HTTP requests and handling

    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
    2019
    +0.29
    1.0%
    876
    +0.23
    0.8%
    674
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.29
    0.04
    946
    +0.23
    0.03
    1678
    +0.14
    0.03
    Negative Logits
     Warszaw
    -0.79
     Yên
    -0.72
    汇总
    -0.70
     Instyt
    -0.70
    渐变
    -0.69
    如下图
    -0.68
     Ślą
    -0.68
    已经有
    -0.67
    自带
    -0.67
     Uniwers
    -0.66
    POSITIVE LOGITS
     dispen
    1.48
     !...
    1.37
     doman
    1.33
     peppa
    1.32
     coq
    1.31
     napoli
    1.31
     matel
    1.30
     jacques
    1.30
     wien
    1.27
     bordeaux
    1.26
    Activations Density 0.124%

    No Known Activations