© 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. 484
    Prev
    Next
    INDEX
    Explanations

    expressions of good luck and congratulations

    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
    +0.24
    0.8%
    152
    +0.07
    0.3%
    2034
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    152
    +0.24
    0.03
    1786
    +0.07
    0.02
    247
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.74
    ⓧ
    -0.73
    <?
    -0.73
    glBind
    -0.66
    CascadeType
    -0.64
    
    
    -0.64
    المشاركات
    -0.62
    SystemColors
    -0.61
    /*
    -0.60
    /*++
    -0.60
    POSITIVE LOGITS
     maneu
    1.60
     reluct
    1.51
     disagre
    1.51
     accla
    1.47
     shenan
    1.44
     eiffel
    1.42
     casio
    1.41
     practition
    1.40
     increa
    1.39
     depic
    1.35
    Activations Density 0.158%

    No Known Activations