© 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. 79
    Prev
    Next
    INDEX
    Explanations

    discussions about negative outcomes and changes in direction related to societal or political progress

    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
    +0.23
    0.8%
    764
    +0.09
    0.3%
    200
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1079
    +0.23
    0.04
    1627
    +0.09
    0.03
    1705
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.28
    app
    -0.61
     put
    -0.59
     do
    -0.58
     feed
    -0.56
     inspect
    -0.56
     distribute
    -0.55
     add
    -0.55
     respond
    -0.55
     serve
    -0.55
    POSITIVE LOGITS
     tricot
    1.36
     nutella
    1.30
     swarovski
    1.30
     churrasco
    1.29
     soggior
    1.29
     applau
    1.28
     bandung
    1.27
     tupperware
    1.27
     pecuni
    1.24
     bordeaux
    1.22
    Activations Density 0.425%

    No Known Activations