© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 349
    Prev
    Next
    INDEX
    Explanations

    biographical details related to a person's education and career beginnings

    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
    +0.38
    1.6%
    198
    +0.13
    0.6%
    453
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1862
    +0.38
    0.07
    1013
    +0.13
    0.07
    509
    +0.12
    0.07
    Negative Logits
    <bos>
    -0.99
     unload
    -0.60
    概
    -0.54
     ter
    -0.52
    <eos>
    -0.51
     our
    -0.50
     rehabilitate
    -0.49
    一
    -0.49
    苗
    -0.49
     reschedule
    -0.49
    POSITIVE LOGITS
     pymysql
    1.11
     Minang
    1.10
     ftre
    1.03
     heapq
    1.02
     leaft
    1.00
     ftu
    0.98
     Karang
    0.98
     ftill
    0.98
     bandung
    0.97
     beft
    0.97
    Activations Density 0.752%

    No Known Activations