© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4825
    Prev
    Next
    INDEX
    Explanations

    information related to motorsports and events involving prominent figures in that field

    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
    1577
    +0.43
    1.9%
    394
    +0.28
    1.2%
    1842
    +0.24
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.43
    0.12
    1842
    +0.28
    0.17
    394
    +0.24
    0.13
    Negative Logits
     indestru
    -0.90
     outlander
    -0.89
     withal
    -0.85
     vhs
    -0.83
     tupperware
    -0.80
     umbre
    -0.79
     michelin
    -0.79
     madonna
    -0.78
     wattpad
    -0.77
     lamborghini
    -0.77
    POSITIVE LOGITS
    Erreferentziak
    0.48
    espé
    0.47
    ↘
    0.45
    ↗
    0.43
    zarchiwizowane
    0.43
    parsedMessage
    0.43
    ਘ
    0.42
    Público
    0.42
    Література
    0.41
    Hochspringen
    0.41
    Activations Density 8.406%

    No Known Activations