© 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. 0-RES-JB
    11. 816
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    +0.07
    0.2%
    252
    +0.06
    0.2%
    1120
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.06
    1343
    +0.06
    0.13
    724
    +0.06
    0.08
    Negative Logits
     strove
    -1.05
    
    -1.01
     endeavored
    -0.95
     impelled
    -0.94
     leaped
    -0.93
     endow
    -0.92
    /**
    -0.92
     betrays
    -0.90
     leapt
    -0.90
     endeavouring
    -0.89
    POSITIVE LOGITS
     alkoh
    1.97
     Kategor
    1.96
     moza
    1.87
     meis
    1.85
     ananas
    1.84
     silikon
    1.81
     karton
    1.77
     elek
    1.76
     hek
    1.76
     utop
    1.74
    Activations Density 0.834%

    No Known Activations