© 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. 3849
    Prev
    Next
    INDEX
    Explanations

    phrases related to security and safety measures

    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
    198
    +0.10
    0.3%
    369
    +0.08
    0.2%
    222
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1317
    +0.10
    0.07
    284
    +0.08
    0.07
    697
    +0.08
    0.07
    Negative Logits
     dises
    -0.65
     territo
    -0.63
    itial
    -0.60
     magis
    -0.58
     teri
    -0.57
     Schrö
    -0.57
     définitivement
    -0.57
     habet
    -0.56
     encomp
    -0.56
     Dokter
    -0.56
    POSITIVE LOGITS
     annually
    0.77
     regularly
    0.77
     daily
    0.75
     yearly
    0.71
     routinely
    0.69
     everyday
    0.66
     periodically
    0.63
     weekly
    0.63
     monthly
    0.63
     Regularly
    0.62
    Activations Density 0.972%

    No Known Activations