© 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. 6202
    Prev
    Next
    INDEX
    Explanations

    the word "think" followed by various contexts or implications

    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
    1515
    +0.15
    0.5%
    1137
    +0.14
    0.5%
    1793
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1515
    +0.15
    0.05
    1137
    +0.14
    0.05
    201
    +0.10
    0.03
    Negative Logits
    Leod
    -0.55
    ಘ
    -0.54
    Namara
    -0.53
    Allister
    -0.53
    Cormack
    -0.51
    Millan
    -0.51
     protokol
    -0.51
     Nes
    -0.49
    Dowell
    -0.47
     laboratorium
    -0.45
    POSITIVE LOGITS
     THINK
    1.21
     Think
    1.13
    Think
    1.10
    think
    1.10
     thinking
    1.10
     think
    1.08
    thinking
    1.03
    Thinking
    1.01
     Thinking
    1.00
     thinks
    0.96
    Activations Density 0.106%

    No Known Activations