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. 279
    Prev
    Next
    INDEX
    Explanations

    acronyms related to computer programming and technology

    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
    1978
    +0.18
    0.5%
    1905
    +0.12
    0.4%
    297
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1654
    +0.18
    0.04
    283
    +0.12
    0.01
    1978
    +0.11
    0.04
    Negative Logits
     marquis
    -0.80
     courtier
    -0.77
     unspeak
    -0.75
     wretch
    -0.75
     beaute
    -0.74
     luxuriant
    -0.74
     princesse
    -0.73
     Hieronymus
    -0.72
     schoolmaster
    -0.72
     shewn
    -0.72
    POSITIVE LOGITS
     Luglio
    0.93
     Giugno
    0.85
    2
    0.84
    3
    0.83
    1
    0.81
     particolar
    0.80
    4
    0.79
     Ottobre
    0.77
    5
    0.77
    7
    0.77
    Activations Density 0.171%

    No Known Activations