© 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. 4171
    Prev
    Next
    INDEX
    Explanations

    programming code elements related to Boolean logic and computer systems

    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
    1343
    +0.14
    0.4%
    51
    +0.09
    0.3%
    1871
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.14
    0.04
    453
    +0.09
    0.03
    1005
    +0.08
    0.03
    Negative Logits
     
    -0.68
     désir
    -0.66
     E
    -0.64
     défi
    -0.64
     fameux
    -0.61
     So
    -0.60
     glean
    -0.60
     Re
    -0.60
     clamour
    -0.59
     Be
    -0.58
    POSITIVE LOGITS
     robus
    1.50
     pecuni
    1.37
     pernic
    1.36
     alkoh
    1.31
     anse
    1.28
     hunde
    1.25
     diagon
    1.25
     silikon
    1.24
     revisor
    1.24
     indeb
    1.23
    Activations Density 0.118%

    No Known Activations