© 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. 11104
    Prev
    Next
    INDEX
    Explanations

    code snippets related to Firebase authentication and database updates

    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
    453
    +0.22
    0.7%
    1042
    +0.17
    0.6%
    876
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.22
    0.03
    825
    +0.17
    0.02
    1871
    +0.13
    0.02
    Negative Logits
    是这样的
    -0.78
    其实是
    -0.78
    的区别
    -0.76
    很简单
    -0.75
    的那个
    -0.74
    来源于
    -0.74
    是从
    -0.74
    的对
    -0.74
    来自于
    -0.74
    就是一个
    -0.74
    POSITIVE LOGITS
     marte
    1.61
     aquare
    1.51
     chèvre
    1.40
     vernac
    1.38
     germain
    1.36
     dises
    1.35
     frambo
    1.33
     nuoc
    1.31
     frau
    1.30
     ananas
    1.30
    Activations Density 0.055%

    No Known Activations