© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 549
    Prev
    Next
    INDEX
    Explanations

    references to containers, particularly buckets and their associated uses

    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
    +0.17
    0.8%
    703
    +0.17
    0.8%
    662
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.17
    0.05
    703
    +0.17
    0.04
    1013
    +0.12
    0.04
    Negative Logits
    <bos>
    -1.67
    //*/
    -0.82
    /***
    -0.76
    ///**
    -0.75
     intersper
    -0.74
     endow
    -0.69
     /**
    -0.66
    ⓧ
    -0.65
    //---
    -0.65
     acquaint
    -0.63
    POSITIVE LOGITS
     bucket
    0.90
     basket
    0.76
     buckets
    0.74
     Bucket
    0.73
    bucket
    0.72
     vessel
    0.70
    basket
    0.69
    Bucket
    0.68
     container
    0.68
     baskets
    0.65
    Activations Density 0.161%

    No Known Activations