© 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. 379
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the significance or importance of a topic or issue

    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
    +0.29
    1.3%
    732
    +0.11
    0.5%
    687
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    687
    +0.29
    0.02
    645
    +0.11
    0.02
    683
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.05
     intersper
    -1.10
     encomp
    -1.09
     endow
    -0.96
    ⓧ
    -0.89
     disambigu
    -0.88
     disbur
    -0.84
     interposed
    -0.82
     gratify
    -0.81
     guarante
    -0.77
    POSITIVE LOGITS
     Bárbara
    1.01
     furg
    0.94
     monaster
    0.89
     Hierro
    0.86
     palio
    0.86
     hunde
    0.85
     tramont
    0.85
     vinci
    0.84
     paloma
    0.84
     ristor
    0.83
    Activations Density 0.080%

    No Known Activations