© 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. 12289
    Prev
    Next
    INDEX
    Explanations

    wavelengths of light and how they are reflected

    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
    674
    +0.31
    1.2%
    184
    +0.22
    0.9%
    876
    +0.20
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.31
    0.02
    163
    +0.22
    0.02
    876
    +0.20
    -0.01
    Negative Logits
     philanth
    -1.53
     maneu
    -1.47
     accla
    -1.46
     shenan
    -1.45
     Khart
    -1.44
     Keny
    -1.41
     depic
    -1.41
     reluct
    -1.40
     pamph
    -1.39
     intrigu
    -1.39
    POSITIVE LOGITS
    <bos>
    0.75
     froh
    0.65
    ipedi
    0.57
     wüns
    0.57
    estinal
    0.56
    LOYEES
    0.55
     obyvatel
    0.55
     transacciones
    0.55
     referrerpolicy
    0.54
    elashes
    0.54
    Activations Density 0.212%

    No Known Activations