© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 279
    Prev
    Next
    INDEX
    Explanations

    the word "hence" and its variations, indicating a focus on causal relationships or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lıyor
    -0.75
     ORG
    -0.75
     Diſ
    -0.73
    ſelf
    -0.69
     
    -0.68
     ―――――
    -0.67
     Casi
    -0.67
    Composable
    -0.66
    offrir
    -0.65
    Fech
    -0.65
    POSITIVE LOGITS
     hence
    1.83
    Hence
    1.79
     Hence
    1.69
    hence
    1.63
     accordingly
    1.13
     consequently
    0.95
     thence
    0.93
    whence
    0.85
    Consequently
    0.77
     correspondingly
    0.74
    Activations Density 0.146%

    No Known Activations