© 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. 0-RES-JB
    11. 2409
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical 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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1909
    +0.10
    0.3%
    1065
    +0.09
    0.3%
    1464
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.10
    0.05
    1120
    +0.09
    0.04
    1252
    +0.09
    0.04
    Negative Logits
    Chất
    -0.78
    Trọng
    -0.72
    Chỉ
    -0.71
    Đối
    -0.70
    Đây
    -0.69
    Ông
    -0.69
    Hiện
    -0.69
    tổng
    -0.69
    EIO
    -0.69
    Với
    -0.68
    POSITIVE LOGITS
     unden
    2.29
     impra
    2.20
     maneu
    2.19
     guarante
    2.17
     inev
    2.15
     compen
    2.10
     secon
    2.10
     suscep
    2.09
     inappro
    2.08
     increa
    2.06
    Activations Density 0.331%

    No Known Activations