© 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. 2235
    Prev
    Next
    INDEX
    Explanations

    phrases associated with the idea of creating a better world

    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
    1.1%
    764
    +0.10
    0.4%
    766
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.29
    0.04
    733
    +0.10
    0.04
    791
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.13
     quitted
    -0.72
     darted
    -0.70
     chanced
    -0.70
     kask
    -0.70
     intersper
    -0.70
     shuddered
    -0.69
     shivered
    -0.68
     peered
    -0.68
     endow
    -0.67
    POSITIVE LOGITS
     soggior
    0.96
     rispond
    0.94
     scopri
    0.92
     bisog
    0.90
     parteci
    0.90
     raccont
    0.90
     sappi
    0.88
     purtroppo
    0.87
     pandan
    0.85
     dicono
    0.85
    Activations Density 0.585%

    No Known Activations