© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7436
    Prev
    Next
    INDEX
    Explanations

    comparisons in sizes and magnitudes

    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
    964
    +0.15
    0.5%
    1314
    +0.10
    0.3%
    939
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.15
    0.07
    939
    +0.10
    0.08
    766
    +0.09
    0.06
    Negative Logits
    šech
    -0.63
     Sardegna
    -0.60
    ypeł
    -0.56
     zove
    -0.56
     bosco
    -0.56
     Muzeum
    -0.54
     guma
    -0.54
     hoga
    -0.54
     Portanto
    -0.52
    idać
    -0.52
    POSITIVE LOGITS
     city
    0.93
     cities
    0.88
     metropolis
    0.76
     City
    0.75
     metropolitan
    0.72
     Cities
    0.71
    City
    0.69
    city
    0.69
     cityscape
    0.68
     urban
    0.66
    Activations Density 0.672%

    No Known Activations