© 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. 829
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs or statements of fact

    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
    +0.13
    0.5%
    1724
    +0.06
    0.2%
    647
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.13
    0.06
    117
    +0.06
    0.04
    1793
    +0.05
    0.05
    Negative Logits
    <bos>
    -2.25
    <tfoot>
    -0.83
     accept
    -0.81
    //
    -0.81
     immer
    -0.80
     colspan
    -0.80
    addComponent
    -0.79
     ran
    -0.79
    using
    -0.79
     државе
    -0.78
    POSITIVE LOGITS
     maneu
    2.86
     affor
    2.74
     stockholm
    2.72
     increa
    2.71
     reluct
    2.66
     strick
    2.64
     accla
    2.60
     depic
    2.59
     inev
    2.56
     wherea
    2.56
    Activations Density 0.215%

    No Known Activations