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. 975
    Prev
    Next
    INDEX
    Explanations

    occurrences of contractions or possessive forms related to the verb "to be."

    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
    1.7%
    478
    +0.13
    0.7%
    381
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.34
    0.12
    1973
    +0.13
    0.10
    1122
    +0.11
    0.09
    Negative Logits
    <bos>
    -1.82
    ⓧ
    -1.09
    /***
    
    -1.06
    <?
    -0.98
    
    
    -0.94
    /**
    -0.88
     ù
    -0.80
    <?
    
    -0.78
     jakarta
    -0.77
     springfox
    -0.76
    POSITIVE LOGITS
    ’
    0.73
    ‘
    0.67
     ‘
    0.65
     “
    0.60
    ’)
    0.57
    “
    0.57
    ”
    0.57
    !’
    0.57
    ’,
    0.57
    ?’
    0.56
    Activations Density 0.931%

    No Known Activations