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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2452
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "too"

    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
    +0.08
    0.2%
    1935
    +0.07
    0.2%
    333
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    940
    +0.08
    0.02
    536
    +0.07
    0.03
    51
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.38
     both
    -0.73
     automatically
    -0.70
     immediately
    -0.70
    hline
    -0.70
     continue
    -0.70
    -0.69
     refer
    -0.68
     directly
    -0.68
    beta
    -0.67
    POSITIVE LOGITS
     accla
    1.83
     emphat
    1.79
     unden
    1.77
     intermitt
    1.74
     effe
    1.71
     embra
    1.71
     maneu
    1.71
     depic
    1.69
     impra
    1.68
     suscep
    1.67
    Activations Density 0.373%

    No Known Activations