© 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. 3584
    Prev
    Next
    INDEX
    Explanations

    statements about the status or existence of challenges and opinions

    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
    +0.28
    1.1%
    1810
    +0.12
    0.4%
    421
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.28
    0.05
    1499
    +0.12
    0.06
    841
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.81
     memorize
    -0.61
     materialize
    -0.60
    
    -0.59
    <?
    -0.59
     customize
    -0.58
    AsUp
    -0.57
     plowed
    -0.57
     synthesize
    -0.57
     localize
    -0.57
    POSITIVE LOGITS
     maksi
    0.87
     ejus
    0.86
     xxvi
    0.85
     magis
    0.83
     quoque
    0.83
     protokol
    0.82
     Minang
    0.82
     karbon
    0.82
     :");
    0.81
     xxiv
    0.81
    Activations Density 0.619%

    No Known Activations