© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1736
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal petitions and political campaigns

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1806
    +0.13
    0.6%
    1124
    +0.13
    0.6%
    1472
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.13
    0.04
    1870
    +0.13
    0.02
    1328
    +0.12
    0.04
    Negative Logits
    <bos>
    -0.98
    Stru
    -0.59
     maging
    -0.57
    Mä
    -0.54
    /***
    -0.54
    LAURA
    -0.51
    隼
    -0.50
    AsUp
    -0.50
     adjour
    -0.50
     frighten
    -0.49
    POSITIVE LOGITS
     Mejía
    0.85
     delegate
    0.73
     arroyo
    0.73
     Ngb
    0.70
     delegates
    0.67
     Cárdenas
    0.67
     Víctor
    0.67
     delegation
    0.66
    endaft
    0.64
     Mónica
    0.63
    Activations Density 0.574%

    No Known Activations