© 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. 2089
    Prev
    Next
    INDEX
    Explanations

    mentions of mechanical processes, machinery, and physical technology developments

    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
    1705
    +0.15
    0.6%
    1256
    +0.14
    0.6%
    506
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.15
    0.03
    1256
    +0.14
    0.02
    1276
    +0.14
    0.02
    Negative Logits
     Normdatei
    -0.64
     krim
    -0.60
     kompati
    -0.57
     minimalis
    -0.57
     akade
    -0.55
     respekt
    -0.55
     vort
    -0.55
     sej
    -0.55
     kug
    -0.54
     kosme
    -0.54
    POSITIVE LOGITS
     mechanics
    1.06
     Mechanic
    1.03
     mechanic
    1.03
     mechanical
    1.02
     MECHAN
    1.02
    MECHAN
    0.99
     Mechanics
    0.98
    mechanical
    0.98
     ecru
    0.98
     Mechanical
    0.96
    Activations Density 0.087%

    No Known Activations