© 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. 1988
    Prev
    Next
    INDEX
    Explanations

    references to books or religious texts, particularly in contexts of presence during translations or critiques

    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
    845
    +0.13
    0.4%
    394
    +0.10
    0.3%
    459
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1301
    +0.13
    0.03
    142
    +0.10
    0.03
    483
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.94
     Administrativna
    -1.08
    /**
    -1.07
    ⓧ
    -1.05
     Italijani
    -1.03
    
    
    -1.00
    <?
    -0.96
    WithIOException
    -0.93
     initComponents
    -0.86
    AsUp
    -0.86
    POSITIVE LOGITS
     Middles
    0.93
    antastic
    0.91
     jaya
    0.86
     jawa
    0.85
     Shakspeare
    0.84
     unlaw
    0.82
     contex
    0.81
     uniqu
    0.81
     seiz
    0.80
     Whence
    0.79
    Activations Density 0.159%

    No Known Activations