© 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. 228
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Bel" and its variations

    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
    1677
    +0.17
    1.1%
    50
    +0.15
    0.9%
    1145
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1677
    +0.17
    0.03
    1145
    +0.15
    0.03
    131
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.34
    HasIndex
    -0.68
     initComponents
    -0.68
    RenderAtEndOf
    -0.65
    mkdirs
    -0.63
    TabIndex
    -0.63
    cookieParser
    -0.61
    enumerate
    -0.61
     GeoNames
    -0.61
    DispatchToProps
    -0.60
    POSITIVE LOGITS
     increa
    1.53
     Bel
    1.49
     maneu
    1.46
     practition
    1.44
     accla
    1.42
     Manufact
    1.41
     inev
    1.39
     thut
    1.38
     reluct
    1.38
     ftu
    1.37
    Activations Density 0.045%

    No Known Activations