© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4045
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of historical figures and locations

    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
    528
    +0.20
    1.1%
    406
    +0.14
    0.8%
    544
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.20
    0.00
    690
    +0.14
    0.05
    1097
    +0.13
    0.06
    Negative Logits
     intersper
    -1.07
     shenan
    -1.07
     disreg
    -1.01
     erad
    -0.99
     hairc
    -0.95
     maneu
    -0.94
     swarovski
    -0.93
     ecru
    -0.92
     guarante
    -0.92
     perfet
    -0.90
    POSITIVE LOGITS
     Hunter
    0.67
     Perth
    0.67
     Newcastle
    0.66
     Candy
    0.66
    Candy
    0.65
     Rut
    0.65
     candy
    0.63
    Rut
    0.62
    Perth
    0.62
    Hunter
    0.61
    Activations Density 0.736%

    No Known Activations