© 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. 6-RES-JB
    6. 7005
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking care of oneself or others and maintaining relationships

    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
    +0.17
    0.7%
    1757
    +0.10
    0.4%
    866
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    890
    +0.17
    0.04
    1926
    +0.10
    0.03
    946
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.41
    
    
    -0.67
    lateinit
    -0.60
    deinit
    -0.59
    /***
    
    -0.58
     disbur
    -0.57
    पि
    -0.56
    /**
    -0.54
    devtool
    -0.53
    <?
    -0.53
    POSITIVE LOGITS
     pank
    1.23
     bandung
    1.22
     seksi
    1.20
     saar
    1.17
     lele
    1.15
     maksi
    1.10
     cæ
    1.09
     naer
    1.08
     kasa
    1.07
     Sén
    1.06
    Activations Density 0.321%

    No Known Activations