© 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. 1933
    Prev
    Next
    INDEX
    Explanations

    references to terrorism and related concepts

    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
    1.5%
    1870
    +0.14
    0.8%
    874
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1480
    +0.26
    0.03
    755
    +0.14
    0.03
    1437
    +0.10
    0.02
    Negative Logits
    <bos>
    -3.12
    //---
    -0.63
    <?
    -0.62
     replenish
    -0.59
     put
    -0.59
    rungsseite
    -0.57
    /*++
    -0.57
    <!--[
    -0.57
    //----
    -0.56
    /*!
    -0.56
    POSITIVE LOGITS
     unwarran
    1.22
     pymysql
    1.15
     Minang
    1.15
     riva
    1.12
     Shakspeare
    1.10
     heapq
    1.08
     liberality
    1.08
     Suom
    1.05
     véhic
    1.05
     Juf
    1.05
    Activations Density 0.027%

    No Known Activations