Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14041
    Prev
    Next
    INDEX
    Explanations

    references to taking tours

    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
    1937
    +0.20
    0.8%
    555
    +0.14
    0.5%
    1023
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.20
    0.03
    555
    +0.14
    0.02
    1492
    +0.12
    0.02
    Negative Logits
     vache
    -0.73
     Venise
    -0.65
     menthe
    -0.65
     boxe
    -0.64
     canne
    -0.59
     Janvier
    -0.59
     Mère
    -0.58
     siff
    -0.58
     Diman
    -0.57
     Église
    -0.56
    POSITIVE LOGITS
     tour
    1.37
    tour
    1.27
     tours
    1.24
     Tour
    1.23
    Tour
    1.17
     TOUR
    1.12
     toured
    1.07
     Tours
    1.04
     touring
    1.03
     tourmaline
    0.97
    Activations Density 0.061%

    No Known Activations