© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 815
    Prev
    Next
    INDEX
    Explanations

    mentions of or interactions with grandmothers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1137
    +0.08
    0.3%
    397
    +0.08
    0.3%
    1376
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    28
    +0.08
    0.03
    881
    +0.08
    0.03
    602
    +0.07
    0.03
    Negative Logits
    <bos>
    -0.83
    ⓧ
    -0.76
    <?
    
    -0.74
    <?
    -0.62
    
    
    -0.62
     expand
    -0.62
    ///**
    -0.62
    const
    -0.61
    public
    -0.61
     define
    -0.60
    POSITIVE LOGITS
     grandmother
    1.98
     grandfather
    1.96
     Grandmother
    1.93
     Grandfather
    1.89
     grandparents
    1.82
     grandma
    1.78
     grandpa
    1.74
    grandmother
    1.73
    grandfather
    1.68
     lola
    1.65
    Activations Density 0.068%

    No Known Activations