© 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. 118
    Prev
    Next
    INDEX
    Explanations

    references to a specific esports team or references to its performance

    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
    411
    +0.14
    0.8%
    1516
    +0.12
    0.7%
    1023
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.14
    0.03
    1343
    +0.12
    0.03
    1056
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.37
    
    -1.08
    <?
    -0.68
    ⓧ
    -0.68
     referenties
    -0.65
    /***
    -0.64
    <?
    -0.64
    <!--
    -0.60
    Diweddarwch
    -0.59
    //{
    -0.59
    POSITIVE LOGITS
     Ts
    1.26
     ts
    1.21
     TS
    1.20
     Tsch
    1.02
    TS
    1.01
    Ts
    0.99
     gabri
    0.96
     tsi
    0.95
     TSM
    0.95
     rodriguez
    0.94
    Activations Density 0.137%

    No Known Activations