© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3038
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate ethical and legal boundaries

    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
    +0.26
    0.9%
    1328
    +0.09
    0.3%
    1705
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.26
    0.03
    423
    +0.09
    0.04
    1135
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.25
     enshr
    -0.56
     intersper
    -0.56
     relive
    -0.55
     pled
    -0.55
     amass
    -0.55
     unify
    -0.54
     devotes
    -0.54
     esternos
    -0.53
     rejoined
    -0.53
    POSITIVE LOGITS
     paradiso
    1.25
     palio
    1.06
     tricot
    1.05
     swarovski
    1.02
     maroc
    1.00
     jawa
    0.99
     sfera
    0.98
     gomma
    0.95
     dott
    0.94
     bicic
    0.93
    Activations Density 0.354%

    No Known Activations