© 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. 171
    Prev
    Next
    INDEX
    Explanations

    references to welding and welding equipment

    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
    489
    +0.12
    0.4%
    795
    +0.08
    0.3%
    976
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.12
    0.05
    1343
    +0.08
    0.05
    690
    +0.08
    0.04
    Negative Logits
    <bos>
    -0.92
     xám
    -0.54
     utr
    -0.53
     odp
    -0.52
     sami
    -0.51
     testify
    -0.51
     verho
    -0.51
     khóc
    -0.50
     спи
    -0.49
    loop
    -0.49
    POSITIVE LOGITS
     Simult
    1.17
     quoique
    1.17
     unden
    1.15
     affor
    1.14
     jorge
    1.13
     philanth
    1.10
     applau
    1.09
     Février
    1.08
     Décembre
    1.08
     bordeaux
    1.07
    Activations Density 0.333%

    No Known Activations