© 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. 4479
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases and court proceedings, as well as incidents of detainment and protests

    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
    478
    +0.12
    0.4%
    776
    +0.11
    0.3%
    332
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.12
    0.06
    303
    +0.11
    0.05
    478
    +0.09
    0.05
    Negative Logits
     vété
    -0.79
     étrang
    -0.78
     cytoplas
    -0.71
     clôture
    -0.71
     témoin
    -0.70
     berea
    -0.70
     oeil
    -0.70
     héro
    -0.69
     éc
    -0.68
     accla
    -0.67
    POSITIVE LOGITS
     existence
    0.68
     presence
    0.61
     demise
    0.61
     appearance
    0.60
     arrival
    0.58
     behalf
    0.57
     fate
    0.54
     plight
    0.54
     arriva
    0.54
     own
    0.53
    Activations Density 0.303%

    No Known Activations