© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7584
    Prev
    Next
    INDEX
    Explanations

    phrases related to wine and wine-related activities

    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
    +0.14
    0.5%
    991
    +0.13
    0.5%
    650
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    991
    +0.14
    0.02
    650
    +0.13
    0.02
    1222
    +0.12
    0.02
    Negative Logits
     paillettes
    -0.60
     apparti
    -0.60
     asisten
    -0.58
     lunedì
    -0.58
     Janvier
    -0.58
     Vainqueur
    -0.57
     brille
    -0.56
     frambo
    -0.56
    Schwer
    -0.56
     Comédie
    -0.56
    POSITIVE LOGITS
     wine
    1.42
     Wine
    1.36
     WINE
    1.28
    wine
    1.27
    Wine
    1.25
     wines
    1.20
     Wines
    0.99
     winery
    0.96
     grape
    0.85
     wineries
    0.85
    Activations Density 0.069%

    No Known Activations