© 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. 8059
    Prev
    Next
    INDEX
    Explanations

    mentions and descriptions of locations and events related to natural disasters

    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
    812
    +0.20
    1.0%
    1896
    +0.18
    0.9%
    1339
    +0.18
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.20
    0.04
    1097
    +0.18
    0.05
    1741
    +0.18
    0.00
    Negative Logits
     ecru
    -1.05
     cushi
    -0.91
    /**
    -0.88
     quitted
    -0.87
     hairc
    -0.85
     userEmail
    -0.81
    ⓧ
    -0.81
     Lmao
    -0.81
     userType
    -0.80
     productName
    -0.80
    POSITIVE LOGITS
     Sandy
    1.40
    Sandy
    1.32
    sandy
    0.69
     sandy
    0.62
     NKC
    0.60
     Rocky
    0.58
     Photographie
    0.57
     ويكيميديا
    0.54
     Gemeinsame
    0.54
    Smarty
    0.54
    Activations Density 0.438%

    No Known Activations