© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 357
    Prev
    Next
    INDEX
    Explanations

    prominent political titles and positions

    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
    50
    +0.16
    0.6%
    198
    +0.10
    0.3%
    1967
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.06
    901
    +0.10
    0.04
    402
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.38
    //---
    -0.60
     AssemblyCompany
    -0.56
     disseminate
    -0.56
    ValueGenerated
    -0.56
     shivered
    -0.55
    void
    -0.54
    public
    -0.52
     springfox
    -0.52
     defray
    -0.52
    POSITIVE LOGITS
     quoique
    1.19
     véhic
    1.05
     Minang
    1.05
     autrefois
    1.02
     bascul
    1.01
     Juf
    1.01
     rafra
    0.99
     cavallo
    0.98
     soigne
    0.97
     Luglio
    0.97
    Activations Density 0.302%

    No Known Activations