© 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. 1624
    Prev
    Next
    INDEX
    Explanations

    words indicating minimal quantity or degree

    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
    +0.20
    1.0%
    897
    +0.14
    0.7%
    849
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    849
    +0.20
    0.03
    991
    +0.14
    0.02
    897
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.42
    ⓧ
    -0.73
    //{
    
    -0.71
    /***
    
    -0.70
    Vegeu
    -0.67
    
    
    -0.64
    glBind
    -0.63
    IEnumerator
    -0.62
    Tú
    -0.60
    <?
    
    -0.60
    POSITIVE LOGITS
     nuoc
    1.21
     chèvre
    1.17
    seigneur
    1.12
     churrasco
    1.11
     jacques
    1.11
     blackpink
    1.10
     broderie
    1.09
     matel
    1.09
     beverly
    1.09
     Minang
    1.08
    Activations Density 0.045%

    No Known Activations