© 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. 109
    Prev
    Next
    INDEX
    Explanations

    references to monetary values, particularly annual financial figures

    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
    +0.26
    1.1%
    2034
    +0.12
    0.5%
    1895
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1456
    +0.26
    0.04
    1110
    +0.12
    0.03
    2034
    +0.09
    0.04
    Negative Logits
    <bos>
    -3.17
    ///**
    -0.80
    /***
    -0.71
    //{
    -0.67
    <!--
    -0.65
    //};
    -0.63
    ⓧ
    -0.63
     AssemblyCompany
    -0.61
    //});
    -0.61
    Vegeu
    -0.58
    POSITIVE LOGITS
     cushi
    1.32
     ecru
    1.29
     tupperware
    1.25
     swarovski
    1.23
     riviera
    1.20
     lidl
    1.20
     ibiza
    1.18
     chrysler
    1.17
     michelin
    1.11
     rancho
    1.11
    Activations Density 0.112%

    No Known Activations