© 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. 14795
    Prev
    Next
    INDEX
    Explanations

    terms related to riots and violence

    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
    964
    +0.14
    0.4%
    1861
    +0.09
    0.3%
    1942
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.14
    0.04
    1782
    +0.09
    0.04
    1556
    +0.09
    0.03
    Negative Logits
    <bos>
    -0.83
     boop
    -0.81
     affez
    -0.80
     sento
    -0.80
     luigi
    -0.80
     trovo
    -0.79
     logitech
    -0.76
     imgur
    -0.76
     hasbro
    -0.76
     wikihow
    -0.75
    POSITIVE LOGITS
     riots
    0.80
     riot
    0.69
     unrest
    0.61
     violence
    0.59
     uprising
    0.58
     erupted
    0.55
    riot
    0.53
     disturbances
    0.52
     demonstrations
    0.51
     Riot
    0.51
    Activations Density 0.307%

    No Known Activations