© 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. 2200
    Prev
    Next
    INDEX
    Explanations

    names and terms related to international organizations and politics, especially focusing on individuals' names and positions

    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
    605
    +0.14
    0.6%
    1407
    +0.12
    0.5%
    636
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.05
    478
    +0.12
    0.02
    227
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.70
    ItemBackground
    -0.91
    Демографія
    -0.86
    principalTable
    -0.84
    Chham
    -0.84
     demografica
    -0.81
     bezeichneter
    -0.80
    AsUp
    -0.77
     مرئيه
    -0.77
    Palmar
    -0.77
    POSITIVE LOGITS
     teresa
    1.50
     sovere
    1.49
     gabri
    1.48
     toledo
    1.46
     Juf
    1.45
     squa
    1.43
     Punj
    1.39
     stockholm
    1.38
     paula
    1.37
     gabriel
    1.36
    Activations Density 0.332%

    No Known Activations