© 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. 56
    Prev
    Next
    INDEX
    Explanations

    terms and statistics related to competitive gameplay in League of Legends

    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
    1842
    +0.14
    0.5%
    50
    +0.11
    0.4%
    1741
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1284
    +0.14
    0.04
    1551
    +0.11
    0.03
    1297
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.04
    /***
    
    -0.69
    addComponent
    -0.59
    ണ്ട
    -0.59
    ثيق
    -0.56
    })();
    
    -0.56
    fill
    -0.56
    //{
    
    -0.56
    xFFFFFF
    -0.55
     مرئيه
    -0.55
    POSITIVE LOGITS
     affor
    1.27
     Pamph
    1.23
     volunte
    1.20
     increa
    1.19
     Intere
    1.18
     impra
    1.17
     riviera
    1.16
     philanth
    1.10
     nece
    1.09
     incess
    1.09
    Activations Density 0.161%

    No Known Activations