© 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. 4067
    Prev
    Next
    INDEX
    Explanations

    warnings or alerts related to potential danger or criminal behavior

    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
    1484
    +0.09
    0.2%
    872
    +0.08
    0.2%
    1526
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1484
    +0.09
    0.05
    1782
    +0.08
    0.04
    284
    +0.07
    0.05
    Negative Logits
     laci
    -0.91
     lele
    -0.90
     teri
    -0.82
     gend
    -0.82
     mef
    -0.81
     ivi
    -0.81
     Keny
    -0.79
     quoc
    -0.78
    geer
    -0.78
     Hano
    -0.77
    POSITIVE LOGITS
     because
    1.17
    because
    1.05
     BECAUSE
    0.97
     porque
    0.89
    Because
    0.84
     fordi
    0.83
     Because
    0.83
     omdat
    0.79
     due
    0.79
     потому
    0.77
    Activations Density 0.515%

    No Known Activations