© 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. 1670
    Prev
    Next
    INDEX
    Explanations

    terms and concepts associated with scientific discourse, especially focusing on physics and its broader impact

    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
    0.9%
    766
    +0.08
    0.3%
    198
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    766
    +0.25
    0.05
    980
    +0.08
    0.04
    1385
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.73
    ⓧ
    -1.00
     engage
    -0.77
     "..\..\..\
    -0.77
    <?
    -0.74
    HasColumnType
    -0.74
     bring
    -0.74
     arrange
    -0.73
    .
    -0.73
     prepare
    -0.72
    POSITIVE LOGITS
     aen
    1.93
     levis
    1.84
     stockholm
    1.84
     fta
    1.83
     milano
    1.81
     maroc
    1.81
     mef
    1.79
     squa
    1.79
     lidl
    1.75
     eiffel
    1.73
    Activations Density 0.595%

    No Known Activations