© 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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 11956
    Prev
    Next
    INDEX
    Explanations

    Phrases indicating contrast or unexpected situations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.12
    0.4%
    1135
    +0.09
    0.3%
    1965
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1374
    +0.12
    0.04
    1370
    +0.09
    0.04
    1965
    +0.09
    0.03
    Negative Logits
     incess
    -0.78
     golfe
    -0.72
     giovanni
    -0.70
     italia
    -0.70
     ciao
    -0.69
     boxe
    -0.68
     schia
    -0.67
     Rois
    -0.67
     sopr
    -0.66
     ordina
    -0.66
    POSITIVE LOGITS
    Apesar
    0.66
     setbacks
    0.59
    Meskipun
    0.58
    Vielleicht
    0.58
    Natürlich
    0.57
    pueden
    0.57
    Vielen
    0.57
    Mesmo
    0.54
    podr
    0.54
     difficulties
    0.53
    Activations Density 0.197%

    No Known Activations