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

    Neuronpedia

    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. 4347
    Prev
    Next
    INDEX
    Explanations

    words related to being persistent and sticking to something

    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
    251
    +0.11
    0.3%
    1805
    +0.10
    0.3%
    1056
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1805
    +0.11
    0.03
    1352
    +0.10
    0.03
    251
    +0.10
    0.03
    Negative Logits
     ekos
    -0.60
     kriminal
    -0.53
     organik
    -0.51
     Strukt
    -0.51
     alkoh
    -0.50
     kosme
    -0.50
    Maze
    -0.48
     dahlia
    -0.47
    Shades
    -0.47
    Quin
    -0.46
    POSITIVE LOGITS
     stick
    1.26
     sticks
    1.19
    stick
    1.14
     Stick
    1.13
     sticking
    1.12
    Stick
    1.11
     stuck
    0.98
     STICK
    0.97
     Sticks
    0.94
    sticks
    0.92
    Activations Density 0.083%

    No Known Activations