© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1342
    Prev
    Next
    INDEX
    Explanations

    phrases that express opinions and critiques related to influence and power dynamics

    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
    +0.24
    0.9%
    991
    +0.10
    0.4%
    1178
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1588
    +0.24
    0.03
    53
    +0.10
    0.03
    1110
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.97
    ⓧ
    -0.67
    PreferredItem
    -0.62
    
    
    -0.59
    /**
    -0.58
    bzero
    -0.54
    żdy
    -0.51
     belangrij
    -0.51
    HasForeignKey
    -0.51
    💼
    -0.50
    POSITIVE LOGITS
     tramont
    1.03
     sappi
    1.02
     churrasco
    1.01
     chèvre
    1.00
     hunde
    0.96
     ananas
    0.96
     mezza
    0.96
     frambo
    0.93
     maroc
    0.91
     utop
    0.91
    Activations Density 0.283%

    No Known Activations