© 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. 10-RES-JB
    11. 1726
    Prev
    Next
    INDEX
    Explanations

    the name "Pete" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1034
    +0.16
    0.9%
    68
    +0.14
    0.8%
    545
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.16
    0.01
    227
    +0.14
    0.04
    1097
    +0.14
    0.03
    Negative Logits
    <bos>
    -0.80
    arrête
    -0.69
     zależ
    -0.63
     apresentam
    -0.60
     dão
    -0.59
     precisamos
    -0.57
     fazia
    -0.57
     encontram
    -0.57
    astéro
    -0.55
     diamond
    -0.54
    POSITIVE LOGITS
     pete
    1.14
    Pete
    1.13
     Pete
    1.08
     Kategor
    0.95
     meis
    0.92
     demen
    0.92
     mef
    0.88
     utop
    0.88
     ideolog
    0.87
     „,
    0.86
    Activations Density 0.248%

    No Known Activations