Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 926
    Prev
    Next
    INDEX
    Explanations

    the verb "is" and its variations representing states or conditions

    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
    +0.34
    1.5%
    1937
    +0.12
    0.5%
    82
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.34
    0.07
    651
    +0.12
    0.04
    1351
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.89
    <?
    -0.95
    
    
    -0.84
    /*
    -0.74
    ⓧ
    -0.70
    /**
    -0.67
    InvalidProtocol
    -0.60
    照
    -0.59
    companion
    -0.59
    #
    -0.58
    POSITIVE LOGITS
     accla
    1.56
     maneu
    1.54
     milf
    1.41
     disgra
    1.40
     impra
    1.39
     increa
    1.39
     affor
    1.35
     hairc
    1.34
     scrat
    1.33
     guarante
    1.30
    Activations Density 0.251%

    No Known Activations