© 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. 3034
    Prev
    Next
    INDEX
    Explanations

    expressions related to uncertainty and assumptions

    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
    1842
    +0.29
    1.2%
    1967
    +0.27
    1.1%
    184
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.29
    0.01
    642
    +0.27
    0.07
    1377
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.38
     intersper
    -1.36
     accla
    -1.17
     reluct
    -1.15
     ineffec
    -1.14
     inappro
    -1.12
     vainly
    -1.12
     apprehen
    -1.12
     encomp
    -1.10
     shenan
    -1.10
    POSITIVE LOGITS
    requently
    0.96
    straint
    0.72
     tragedia
    0.72
    GYPT
    0.70
    quante
    0.70
     jawa
    0.70
    Zeneca
    0.69
    requent
    0.69
     tenda
    0.69
     borsa
    0.67
    Activations Density 1.797%

    No Known Activations