© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 506
    Prev
    Next
    INDEX
    Explanations

    phrases that imply achievement or elevated status

    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
    +0.22
    0.9%
    1174
    +0.13
    0.5%
    1565
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1174
    +0.22
    0.03
    537
    +0.13
    0.04
    1512
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.83
     initComponents
    -0.57
     mis
    -0.55
    Ау
    -0.54
     look
    -0.53
    RegressionTest
    -0.53
     don
    -0.52
    look
    -0.50
    <b>
    -0.50
    Fe
    -0.50
    POSITIVE LOGITS
     milf
    1.40
     disgra
    1.27
     bandung
    1.22
     swarovski
    1.19
     peppa
    1.18
     blackpink
    1.18
     lamborghini
    1.16
     pixar
    1.16
     emphat
    1.16
     hilux
    1.16
    Activations Density 0.225%

    No Known Activations