© 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. 2261
    Prev
    Next
    INDEX
    Explanations

    web browser-related terms

    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
    1407
    +0.13
    0.5%
    1870
    +0.12
    0.4%
    1092
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1407
    +0.13
    0.02
    1092
    +0.12
    0.02
    1637
    +0.11
    0.02
    Negative Logits
     fann
    -0.56
     Konkur
    -0.56
     madden
    -0.56
     Akismet
    -0.54
     hilux
    -0.52
     deere
    -0.51
     Joi
    -0.51
     joi
    -0.49
     antici
    -0.49
     floyd
    -0.49
    POSITIVE LOGITS
     browser
    1.37
    browser
    1.28
     Browser
    1.21
     browsers
    1.17
    Browser
    1.15
    浏览器
    0.87
     Brows
    0.86
    rowser
    0.86
    browsers
    0.83
    WSER
    0.77
    Activations Density 0.053%

    No Known Activations