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. 6-RES-JB
    6. 6049
    Prev
    Next
    INDEX
    Explanations

    references to mother figures or concepts related to motherhood

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.19
    1.1%
    596
    +0.10
    0.6%
    506
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.19
    0.04
    1110
    +0.10
    0.03
    1515
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.33
    /***
    
    -0.85
    <?
    -0.78
    IonicModule
    -0.77
    ⓧ
    -0.72
    HasColumnType
    -0.71
    <?
    
    -0.70
    VStack
    -0.70
    HasIndex
    -0.69
    lateinit
    -0.69
    POSITIVE LOGITS
     Juf
    1.48
     Momb
    1.44
     véhic
    1.33
     Jambi
    1.27
     stockholm
    1.26
     soulign
    1.25
     ricardo
    1.25
     ibiza
    1.23
     riviera
    1.21
     sergio
    1.20
    Activations Density 0.100%

    No Known Activations