© 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. 10-RES-JB
    11. 64
    Prev
    Next
    INDEX
    Explanations

    references to Sweden and its attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    442
    +0.16
    0.9%
    406
    +0.15
    0.8%
    1480
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.16
    0.03
    1480
    +0.15
    0.03
    227
    +0.15
    0.03
    Negative Logits
    <bos>
    -1.92
    Servus
    -0.63
    /***
    -0.60
     subside
    -0.60
    <?
    -0.60
     NKC
    -0.59
    //{
    -0.58
     dissipate
    -0.58
    DockStyle
    -0.58
     consolidate
    -0.57
    POSITIVE LOGITS
     Swedes
    1.27
     Swedish
    1.23
     Sweden
    1.21
    Sweden
    1.21
    Swedish
    1.17
     sweden
    1.04
     swedish
    1.03
     Swe
    1.01
     quoique
    0.99
     sué
    0.98
    Activations Density 0.152%

    No Known Activations