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. 1237
    Prev
    Next
    INDEX
    Explanations

    instances of contractions, specifically the word "’s"

    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
    +0.21
    0.8%
    2019
    +0.09
    0.3%
    478
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1923
    +0.21
    0.04
    1090
    +0.09
    0.04
    145
    +0.08
    0.04
    Negative Logits
    <bos>
    -1.66
    ⓧ
    -1.14
    
    
    -1.02
     intersper
    -0.91
    <?
    -0.88
    /***
    
    -0.82
     disbur
    -0.81
    /**
    -0.80
     defray
    -0.80
    Transcripción
    -0.78
    POSITIVE LOGITS
     kedi
    0.72
    ()")
    0.67
    siyah
    0.64
     Muhamma
    0.63
     seksi
    0.63
    =]
    0.62
     hermosos
    0.62
     bicic
    0.62
    "");
    0.61
     jawa
    0.61
    Activations Density 0.065%

    No Known Activations