© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6008
    Prev
    Next
    INDEX
    Explanations

    terms related to guiding or instructing others and innovation

    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
    +0.21
    0.8%
    1387
    +0.13
    0.5%
    897
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    897
    +0.21
    0.06
    1387
    +0.13
    0.05
    2000
    +0.08
    0.05
    Negative Logits
    <bos>
    -1.89
    /**
    -0.71
     propose
    -0.65
    ⓧ
    -0.64
    
    -0.63
     began
    -0.63
     started
    -0.62
     also
    -0.62
     spoke
    -0.61
     begin
    -0.59
    POSITIVE LOGITS
     saar
    1.33
     lele
    1.31
     jaya
    1.30
     maksi
    1.29
     gomma
    1.28
     maroc
    1.28
     ceramica
    1.27
     autunno
    1.27
     levis
    1.27
     Juf
    1.27
    Activations Density 0.520%

    No Known Activations