© 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. 11964
    Prev
    Next
    INDEX
    Explanations

    references to contests or competitions

    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
    411
    +0.20
    0.8%
    805
    +0.15
    0.7%
    1323
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.20
    0.04
    805
    +0.15
    0.03
    1323
    +0.14
    0.02
    Negative Logits
     Bab
    -0.51
     Aly
    -0.47
     parco
    -0.47
    Bab
    -0.46
     Schro
    -0.46
    Aly
    -0.46
     Pul
    -0.46
    Giu
    -0.45
    Pul
    -0.45
    Ano
    -0.44
    POSITIVE LOGITS
     CONTEST
    1.02
     contest
    1.01
     Cont
    0.98
     contests
    0.98
     Contest
    0.97
    contest
    0.92
     CONT
    0.88
    Contest
    0.88
    CONT
    0.87
    Cont
    0.85
    Activations Density 0.108%

    No Known Activations