© 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. 7137
    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
    +0.28
    1.0%
    1305
    +0.04
    0.1%
    1870
    +0.04
    0.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.28
    0.00
    0
    -0.04
    0.00
    1
    -0.04
    0.00
    Negative Logits
     unspeak
    -2.87
     reluct
    -2.75
     unlaw
    -2.60
     impractica
    -2.55
     shenan
    -2.54
     disagre
    -2.53
     indestru
    -2.44
     impra
    -2.39
     apprehen
    -2.38
     disgra
    -2.37
    POSITIVE LOGITS
    <bos>
    9.77
    GEBURTSDATUM
    1.96
    Autoritní
    1.95
    expandindo
    1.85
    تقاوى
    1.76
    Personendaten
    1.75
     betweenstory
    1.72
     '\\;'
    1.71
     للاسماء
    1.68
     autorytatywna
    1.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.