© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 197
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location, Rio de Janeiro

    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
    2011
    +0.12
    0.4%
    1103
    +0.09
    0.2%
    1350
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.12
    0.02
    1656
    +0.09
    0.02
    1721
    +0.08
    0.02
    Negative Logits
    直
    -0.70
     “
    -0.69
     appear
    -0.69
     for
    -0.69
     га
    -0.69
     необходимость
    -0.68
     fix
    -0.68
    各
    -0.68
     can
    -0.68
     ли
    -0.67
    POSITIVE LOGITS
     Rio
    2.35
    Rio
    2.18
     RIO
    2.14
     affor
    2.09
     accla
    1.94
     increa
    1.92
     embodi
    1.85
     fta
    1.84
     stockholm
    1.84
     unden
    1.81
    Activations Density 0.191%

    No Known Activations