© 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. 1374
    Prev
    Next
    INDEX
    Explanations

    descriptors related to features and specifications of products, particularly in a technical context

    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
    1.0%
    1385
    +0.20
    0.8%
    1343
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.26
    0.13
    678
    +0.20
    0.09
    16
    +0.18
    0.08
    Negative Logits
    <bos>
    -2.03
    HasAnnotation
    -0.74
    ValueGenerated
    -0.74
    Autoritní
    -0.65
    AutoField
    -0.64
    /***
    
    -0.64
     насеља
    -0.63
     breathed
    -0.63
    beforeAll
    -0.62
     suddenly
    -0.62
    POSITIVE LOGITS
     affez
    1.39
     aen
    1.30
     soggior
    1.22
     embodi
    1.19
     lele
    1.13
     lyon
    1.10
     aspetta
    1.09
     uncin
    1.08
     Décembre
    1.08
     trovo
    1.08
    Activations Density 0.694%

    No Known Activations