© 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. 3637
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or dependencies in scenarios

    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
    +0.17
    0.6%
    30
    +0.07
    0.2%
    1218
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.17
    0.07
    1784
    +0.07
    0.06
    1055
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.17
    Autoritní
    -0.71
    CreateMap
    -0.57
     harmonize
    -0.55
     modernize
    -0.55
    вік
    -0.53
     supervis
    -0.53
     supervise
    -0.52
    Fris
    -0.51
     oversee
    -0.51
    POSITIVE LOGITS
     ecru
    1.01
     toti
    0.99
     pylab
    0.99
     împre
    0.96
     nutella
    0.95
     tupperware
    0.93
     camry
    0.92
     pymysql
    0.91
     swarovski
    0.90
     hilux
    0.89
    Activations Density 0.509%

    No Known Activations