© 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. 1692
    Prev
    Next
    INDEX
    Explanations

    references to a specific location, specifically focusing on the Philippines

    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
    1331
    +0.10
    0.3%
    892
    +0.09
    0.3%
    438
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.03
    438
    +0.09
    0.03
    1832
    +0.09
    0.02
    Negative Logits
    流
    -0.85
    ше
    -0.85
    англ
    -0.85
     const
    -0.84
     ра
    -0.83
    ,
    -0.82
     des
    -0.82
     will
    -0.82
    .
    -0.82
     наме
    -0.82
    POSITIVE LOGITS
     affor
    2.98
     emphat
    2.97
     wien
    2.97
     increa
    2.92
     stockholm
    2.91
     philippines
    2.86
     effe
    2.85
     maneu
    2.83
     fta
    2.83
     fte
    2.81
    Activations Density 0.248%

    No Known Activations