© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2661
    Prev
    Next
    INDEX
    Explanations

    phrases related to quitting or cessation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.19
    1.0%
    1416
    +0.11
    0.6%
    1233
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.19
    0.01
    1805
    +0.11
    0.01
    260
    +0.11
    0.01
    Negative Logits
    <bos>
    -2.29
    介
    -0.58
    holder
    -0.57
    المكان
    -0.54
    bee
    -0.54
    @
    -0.53
    Pag
    -0.53
    Fe
    -0.52
     ensure
    -0.52
    גרפיה
    -0.52
    POSITIVE LOGITS
     Minang
    1.17
     ecru
    1.13
     swarovski
    1.12
     maroc
    1.10
     Quit
    1.09
     Juf
    1.09
     quitting
    1.08
     quitt
    1.08
     QUIT
    1.07
     hairc
    1.06
    Activations Density 0.039%

    No Known Activations