© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 373
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time, specifically focusing on the term "years ago."

    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
    +0.31
    1.6%
    2034
    +0.12
    0.6%
    1194
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1194
    +0.31
    0.04
    1376
    +0.12
    0.03
    12
    +0.10
    0.02
    Negative Logits
    <bos>
    -3.15
    arr
    -0.68
    public
    -0.66
    char
    -0.63
    mat
    -0.62
    tri
    -0.61
    mu
    -0.61
    struct
    -0.61
    circ
    -0.61
     manage
    -0.61
    POSITIVE LOGITS
     maneu
    1.75
     milf
    1.60
     reluct
    1.60
     madonna
    1.60
     affor
    1.57
     beverly
    1.57
     stockholm
    1.56
     disagre
    1.54
     shenan
    1.54
     maroc
    1.52
    Activations Density 0.050%

    No Known Activations