© 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. 13367
    Prev
    Next
    INDEX
    Explanations

    sports-related terms such as player names and skills

    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
    394
    +0.26
    0.8%
    856
    +0.24
    0.8%
    764
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.26
    0.07
    764
    +0.24
    0.06
    856
    +0.17
    0.05
    Negative Logits
    isenberg
    -0.53
    зулта
    -0.50
    ècie
    -0.49
    SourceChecksum
    -0.48
     patin
    -0.46
    dames
    -0.46
     bezeichneter
    -0.45
    ांकि
    -0.45
     afirm
    -0.44
    featureID
    -0.44
    POSITIVE LOGITS
     chrysler
    0.69
     embodi
    0.67
     chevrolet
    0.64
     lamborghini
    0.63
    volkswagen
    0.62
     volkswagen
    0.61
    Dzięki
    0.60
     hilux
    0.60
     scrat
    0.59
     withal
    0.59
    Activations Density 0.684%

    No Known Activations