© 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. 15-GEMMASCOPE-RES-16K
    11. 8988
    Prev
    Next
    INDEX
    Explanations

    intensifying or amplifying adverbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.70
     Jackman
    -0.70
     sauvages
    -0.67
     trecut
    -0.66
    ActionTypes
    -0.62
     toscana
    -0.61
    ded
    -0.61
     Gillette
    -0.60
     segü
    -0.60
     tanga
    -0.60
    POSITIVE LOGITS
     very
    1.02
     Very
    1.01
     VERY
    0.98
    VERY
    0.95
    Very
    0.93
    very
    0.93
    Molto
    0.84
    Muy
    0.79
    sehr
    0.79
    umato
    0.75
    Activations Density 0.041%

    No Known Activations