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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14183
    Prev
    Next
    INDEX
    Explanations

    mentions of "British" and "Britain"

    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
    1984
    +0.13
    0.5%
    528
    +0.12
    0.4%
    553
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.13
    0.04
    1984
    +0.12
    0.03
    1506
    +0.11
    0.03
    Negative Logits
     "..\..\..\
    -0.58
     "..\..\
    -0.56
    Pozdrawiam
    -0.46
    actrice
    -0.45
    principalColumn
    -0.45
    ಅ
    -0.43
    
    -0.42
     deere
    -0.42
    multer
    -0.42
    <?
    -0.42
    POSITIVE LOGITS
     British
    1.19
     Áng
    1.15
     Britain
    1.14
    British
    1.14
    Britain
    1.04
     british
    1.04
     Marín
    1.02
     Brit
    0.96
     brit
    0.94
     Brits
    0.93
    Activations Density 0.087%

    No Known Activations