© 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. 5823
    Prev
    Next
    INDEX
    Explanations

    phrases related to government, policy, and accountability

    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
    50
    +0.20
    0.9%
    604
    +0.15
    0.7%
    1499
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.20
    0.16
    344
    +0.15
    -0.01
    1048
    +0.11
    0.04
    Negative Logits
    <bos>
    -3.34
    anță
    -0.99
     realize
    -0.83
    AVOR
    -0.83
    ⓧ
    -0.82
     utilize
    -0.82
    ății
    -0.80
     color
    -0.80
     personalize
    -0.79
     neighborhoods
    -0.79
    POSITIVE LOGITS
     soulign
    1.43
     McLaugh
    1.40
     Juf
    1.36
     tucson
    1.29
     véhic
    1.28
     unlaw
    1.26
     Bartholo
    1.26
     Gorb
    1.26
     impractica
    1.25
     Rine
    1.21
    Activations Density 3.866%

    No Known Activations