Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 10051
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts like pointers, callbacks, and memory management

    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
    876
    +0.18
    0.5%
    334
    +0.12
    0.4%
    857
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.18
    0.00
    1511
    +0.12
    0.01
    836
    +0.10
    0.01
    Negative Logits
     kosme
    -0.83
     akut
    -0.80
     vertik
    -0.76
     Demok
    -0.76
     Demokrat
    -0.75
     radikal
    -0.74
     Singapur
    -0.74
     akus
    -0.73
     Komis
    -0.73
     kriminal
    -0.73
    POSITIVE LOGITS
     peppa
    0.99
     nutella
    0.99
     parma
    0.98
     michelin
    0.97
     oreo
    0.97
     scrat
    0.94
     affor
    0.92
     tupperware
    0.91
     oleo
    0.85
     encomp
    0.84
    Activations Density 0.147%

    No Known Activations