© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4616
    Prev
    Next
    INDEX
    Explanations

    terms related to contemplation and reflection

    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
    1137
    +0.15
    0.7%
    369
    +0.13
    0.5%
    680
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.15
    0.05
    1137
    +0.13
    0.05
    1013
    +0.12
    0.05
    Negative Logits
    <bos>
    -2.06
    displayquote
    -0.68
     contact
    -0.68
    InputTagHelper
    -0.67
    DN
    -0.67
    catch
    -0.66
    join
    -0.66
    contact
    -0.66
    if
    -0.65
     thu
    -0.65
    POSITIVE LOGITS
     increa
    1.73
     impra
    1.69
     scrat
    1.67
     unce
    1.64
     fta
    1.60
     sovere
    1.57
     swarovski
    1.57
     excru
    1.55
     unden
    1.52
     friable
    1.52
    Activations Density 0.261%

    No Known Activations