© 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. 4094
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    +0.26
    0.8%
    1853
    +0.06
    0.2%
    1323
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.26
    0.00
    0
    -0.06
    0.00
    1
    -0.06
    0.00
    Negative Logits
     reluct
    -3.25
     impra
    -3.14
     unspeak
    -3.01
     disagre
    -2.90
     depic
    -2.90
     shenan
    -2.89
     increa
    -2.88
     unve
    -2.88
     impractica
    -2.88
     maneu
    -2.85
    POSITIVE LOGITS
    <bos>
    6.83
     Walkover
    1.53
    GEBURTSDATUM
    1.48
     Paglinawan
    1.45
    Personendaten
    1.43
     betweenstory
    1.38
    expandindo
    1.32
     kaarangay
    1.30
     PicClick
    1.29
    脚注の使い方
    1.28
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.