© 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. 514
    Prev
    Next
    INDEX
    Explanations

    phrases expressing disagreement

    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
    +0.22
    0.9%
    605
    +0.10
    0.4%
    201
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.22
    0.03
    276
    +0.10
    0.03
    889
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.24
    
    -0.79
    /*
    -0.70
    /**
    -0.69
    <?
    -0.67
    run
    -0.58
    /***
    -0.58
    static
    -0.57
    establish
    -0.56
    pitch
    -0.55
    POSITIVE LOGITS
     maroc
    1.32
     Minang
    1.31
     Sén
    1.31
     milano
    1.24
     bandung
    1.22
     stockholm
    1.22
     lidl
    1.22
     madonna
    1.22
     Docteur
    1.21
     cartier
    1.20
    Activations Density 0.110%

    No Known Activations