© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14836
    Prev
    Next
    INDEX
    Explanations

    the word "very" in various contexts

    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
     culturelles
    -0.87
     sauvages
    -0.83
     religieuses
    -0.79
     financières
    -0.78
     houſe
    -0.77
     scolaires
    -0.75
     vertes
    -0.75
     anhänger
    -0.72
     alimentaires
    -0.72
     ainfi
    -0.71
    POSITIVE LOGITS
     very
    1.93
     Very
    1.69
    Very
    1.63
    very
    1.56
     VERY
    1.46
    VERY
    1.41
     muy
    1.31
     très
    1.30
    очень
    1.12
     sehr
    1.08
    Activations Density 0.111%

    No Known Activations