© 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. 13392
    Prev
    Next
    INDEX
    Explanations

    phrases related to practice, preparation, and dedication

    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
    1222
    +0.16
    0.6%
    795
    +0.14
    0.5%
    486
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1222
    +0.16
    0.03
    795
    +0.14
    0.02
    1562
    +0.13
    0.02
    Negative Logits
     nadat
    -0.45
     afgelopen
    -0.45
    rası
    -0.44
     gesteld
    -0.44
     juegan
    -0.44
     felici
    -0.44
    hyrchwyd
    -0.42
     palk
    -0.42
    حياته
    -0.42
    кульп
    -0.42
    POSITIVE LOGITS
     Van
    1.39
    Van
    1.32
     VAN
    1.31
     van
    1.20
    VAN
    1.10
    van
    1.08
     vans
    0.97
     Vans
    0.96
     répon
    0.95
     exé
    0.83
    Activations Density 0.062%

    No Known Activations