© 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. 21-GEMMASCOPE-RES-16K
    11. 12878
    Prev
    Next
    INDEX
    Explanations

    intensifiers or adverbs that amplify the degree of an adjective or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teljesen
    -0.73
     Fully
    -0.62
     tamamen
    -0.61
     entièrement
    -0.61
     constamment
    -0.60
     coû
    -0.60
     tikra
    -0.60
    Fully
    -0.59
     muito
    -0.59
     واقعا
    -0.58
    POSITIVE LOGITS
     important
    0.67
     efficient
    0.66
     powerful
    0.62
     clever
    0.61
     valuable
    0.60
     accurate
    0.59
    новништво
    0.59
     sensitive
    0.59
     tight
    0.59
    StoryboardSegue
    0.59
    Activations Density 0.160%

    No Known Activations