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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 578
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or acknowledgment in texts

    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
    50
    +0.12
    0.4%
    1027
    +0.06
    0.2%
    998
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1027
    +0.12
    0.04
    356
    +0.06
    0.03
    998
    +0.06
    0.03
    Negative Logits
    /**
    -1.23
    ⓧ
    -1.21
    <?
    -1.20
    /*
    -1.12
    
    
    -1.12
    #
    -0.98
     "..\..\..\
    -0.86
    <?
    
    -0.85
    JAKARTA
    -0.77
    ValueGenerated
    -0.77
    POSITIVE LOGITS
     maneu
    2.38
     accla
    2.32
     depic
    2.22
     impra
    2.14
     suscep
    2.13
     emphat
    2.12
     indestru
    2.12
     erad
    2.12
     inev
    2.11
     reluct
    2.08
    Activations Density 0.252%

    No Known Activations