© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6227
    Prev
    Next
    INDEX
    Explanations

    mentions of the United Kingdom

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    568
    +0.11
    0.4%
    1757
    +0.11
    0.4%
    156
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1304
    +0.11
    0.03
    568
    +0.11
    0.03
    156
    +0.11
    0.03
    Negative Logits
    principalColumn
    -0.69
     "..\..\
    -0.62
    UnusedPrivate
    -0.61
    Referencies
    -0.60
    Segoe
    -0.59
    portál
    -0.58
     poveznice
    -0.58
     referenties
    -0.57
    osoba
    -0.57
    hadores
    -0.56
    POSITIVE LOGITS
    UK
    1.11
     UK
    1.10
     Simult
    1.06
     unlaw
    1.05
     Incenti
    1.03
     Juf
    1.00
     viciss
    0.99
     maneu
    0.99
     perfet
    0.98
     Byp
    0.97
    Activations Density 0.053%

    No Known Activations