© 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. 456
    Prev
    Next
    INDEX
    Explanations

    references to licenses, particularly related to Creative Commons

    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
    +0.22
    0.8%
    1343
    +0.12
    0.5%
    1150
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.22
    0.03
    185
    +0.12
    0.02
    1802
    +0.11
    0.02
    Negative Logits
    <bos>
    -3.07
     betweenstory
    -0.90
    LayoutStyle
    -0.89
    InputBorder
    -0.81
     initComponents
    -0.79
     ModelExpression
    -0.79
     gainera
    -0.77
    InjectMocks
    -0.77
    DeleteMapping
    -0.75
     Spisak
    -0.75
    POSITIVE LOGITS
     maneu
    1.87
     affor
    1.72
     disreg
    1.62
     intermitt
    1.56
     milano
    1.54
     impra
    1.51
     scrat
    1.49
     increa
    1.48
     resear
    1.48
     accla
    1.44
    Activations Density 0.040%

    No Known Activations