© 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. 10-RES-JB
    11. 4321
    Prev
    Next
    INDEX
    Explanations

    references to the development, credibility, and changing dynamics of organizations, specifically in sports and religion

    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
    +0.30
    1.1%
    764
    +0.11
    0.4%
    562
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    562
    +0.30
    0.06
    764
    +0.11
    0.04
    2000
    +0.08
    0.05
    Negative Logits
    <bos>
    -2.29
    ItemBackground
    -0.57
    <?
    -0.56
    /*!
    -0.52
    arch
    -0.51
    /**
    -0.51
    /*++
    -0.50
     neutralize
    -0.50
    Erreferentziak
    -0.50
    ствовали
    -0.49
    POSITIVE LOGITS
     tupperware
    1.47
     nutella
    1.33
     pandan
    1.28
     ecru
    1.27
     lidl
    1.22
     oreo
    1.21
     napoli
    1.20
     peppa
    1.19
     bonbons
    1.18
     cavallo
    1.17
    Activations Density 1.120%

    No Known Activations