© 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. 453
    Prev
    Next
    INDEX
    Explanations

    instances of the word "seen" and expressions of familiarity or comparison

    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
    +0.25
    1.1%
    1392
    +0.14
    0.6%
    1678
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.25
    0.04
    1678
    +0.14
    0.04
    1491
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.77
     instead
    -0.63
     continue
    -0.63
     plug
    -0.62
    2
    -0.62
    <eos>
    -0.61
    ನ್ನ
    -0.61
    continue
    -0.61
    <?
    -0.61
    plug
    -0.61
    POSITIVE LOGITS
     fta
    1.77
     Minang
    1.75
     Juf
    1.71
     increa
    1.71
     guarante
    1.67
     aen
    1.65
     thut
    1.62
     bandung
    1.62
     ftu
    1.61
     jawa
    1.59
    Activations Density 0.121%

    No Known Activations