© 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. 551
    Prev
    Next
    INDEX
    Explanations

    terms related to non-traditional or non-conforming identities

    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
    +0.25
    1.3%
    1262
    +0.11
    0.6%
    1994
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1370
    +0.25
    0.05
    1994
    +0.11
    0.04
    1262
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.15
    ⓧ
    -0.75
    /**
    -0.69
    <?
    -0.67
     continue
    -0.67
    /*++
    -0.67
    
    -0.65
    ValueGenerated
    -0.65
     also
    -0.64
     do
    -0.64
    POSITIVE LOGITS
     sovere
    1.70
     aen
    1.68
     Juf
    1.68
     secon
    1.66
     ftu
    1.64
     Intere
    1.61
     fta
    1.60
     effe
    1.60
     increa
    1.59
     viciss
    1.59
    Activations Density 0.038%

    No Known Activations