© 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. 2039
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical or statistical concepts and structures

    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
    876
    +0.19
    0.8%
    1177
    +0.17
    0.7%
    1842
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1577
    +0.19
    0.15
    678
    +0.17
    0.11
    1385
    +0.15
    0.12
    Negative Logits
    <bos>
    -1.85
    UpInside
    -0.85
    GOTREF
    -0.79
    opcao
    -0.77
    ValueGenerated
    -0.73
    Показать
    -0.72
    CreateIndex
    -0.72
    Crítica
    -0.72
    Pró
    -0.71
    ILayout
    -0.71
    POSITIVE LOGITS
     embodi
    2.63
     fluo
    2.57
     wien
    2.52
     effe
    2.44
     emphat
    2.43
     increa
    2.43
     squa
    2.40
     napoli
    2.39
     maneu
    2.38
     mef
    2.37
    Activations Density 2.304%

    No Known Activations