© 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. 13279
    Prev
    Next
    INDEX
    Explanations

    situations involving debates or discussions surrounding societal issues or controversial topics

    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
    1253
    +0.15
    0.5%
    478
    +0.13
    0.4%
    2034
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1533
    +0.15
    0.06
    610
    +0.13
    0.09
    478
    +0.13
    0.07
    Negative Logits
    Derp
    -0.95
    Lma
    -0.89
    Cringe
    -0.89
    Yess
    -0.87
    Yeet
    -0.81
    Noice
    -0.79
    Fuckin
    -0.79
    Oof
    -0.77
    Whoo
    -0.77
     shenan
    -0.76
    POSITIVE LOGITS
     paradiso
    0.88
     palio
    0.85
     torba
    0.81
    pendente
    0.81
     riva
    0.81
     bronzo
    0.78
     virtù
    0.77
     Settembre
    0.76
     sopr
    0.76
     Ottobre
    0.76
    Activations Density 0.400%

    No Known Activations