© 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. 1727
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to individuals or characters

    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
    889
    +0.16
    0.9%
    1480
    +0.14
    0.8%
    204
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.16
    0.04
    1343
    +0.14
    0.04
    889
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.92
    Probl
    -0.73
    /*
    -0.68
    ⓧ
    -0.67
    Día
    -0.67
    Assista
    -0.66
    Serviço
    -0.66
    asteroido
    -0.65
    JspWriter
    -0.64
    Pratique
    -0.63
    POSITIVE LOGITS
     maneu
    1.87
     affor
    1.71
     increa
    1.68
     depic
    1.66
     reluct
    1.61
     strick
    1.60
     erad
    1.60
     unden
    1.59
     disagre
    1.59
     milf
    1.59
    Activations Density 0.190%

    No Known Activations