© 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. 1506
    Prev
    Next
    INDEX
    Explanations

    references to specific types of clothing and associated accessories

    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
    1343
    +0.24
    0.9%
    1385
    +0.16
    0.6%
    1013
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.24
    0.11
    678
    +0.16
    0.07
    1842
    +0.13
    0.05
    Negative Logits
    <bos>
    -2.57
    HasIndex
    -0.84
    /**
    -0.83
    
    -0.83
    InjectMocks
    -0.82
    DockStyle
    -0.81
    ⓧ
    -0.80
    HasForeignKey
    -0.79
    RemoveField
    -0.79
    Sqft
    -0.77
    POSITIVE LOGITS
     uncin
    1.22
     ferru
    1.09
     affez
    1.05
     embodi
    1.04
     pym
    1.02
     Juf
    1.02
     pollut
    1.00
     magis
    1.00
     viciss
    0.99
     nomine
    0.98
    Activations Density 0.581%

    No Known Activations