© 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. 2941
    Prev
    Next
    INDEX
    Explanations

    references to quantity and amounts

    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%
    369
    +0.11
    0.4%
    990
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1569
    +0.24
    0.04
    369
    +0.11
    0.03
    1526
    +0.10
    0.03
    Negative Logits
    <bos>
    -1.88
     shrank
    -0.56
    addCriterion
    -0.55
    /**
    -0.54
     shuddered
    -0.52
     harmonize
    -0.52
     modernize
    -0.49
     reinstate
    -0.49
     broadened
    -0.48
     saluted
    -0.48
    POSITIVE LOGITS
     asado
    0.92
     papà
    0.91
     Spent
    0.91
     signor
    0.91
     churrasco
    0.90
    Spent
    0.90
     predecess
    0.87
     Spend
    0.87
     fianco
    0.86
     monaster
    0.86
    Activations Density 0.139%

    No Known Activations