© 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. 1308
    Prev
    Next
    INDEX
    Explanations

    concepts related to foundational elements or principles

    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
    +0.25
    1.0%
    1705
    +0.14
    0.5%
    297
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.25
    0.04
    872
    +0.14
    0.04
    186
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.09
     liberate
    -0.59
     mobilize
    -0.55
     synchronize
    -0.55
     inaugurate
    -0.54
     implore
    -0.53
     harmonize
    -0.53
    /*!
    
    -0.52
    DotNetBar
    -0.51
    /***
    
    -0.51
    POSITIVE LOGITS
     palio
    1.20
     paradiso
    1.12
     foundation
    1.08
     foundations
    1.05
     divertimento
    1.05
     affez
    0.98
     ristor
    0.97
     soste
    0.96
     autunno
    0.95
     predecess
    0.94
    Activations Density 0.254%

    No Known Activations