© 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. 20-GEMMASCOPE-RES-16K
    11. 5517
    Prev
    Next
    INDEX
    Explanations

    references to support, community engagement, and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before adverbs or action-oriented words

    np_acts-logits-general · gemini-2.0-flash

    manner of action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.82
     auffi
    -0.81
     ſtate
    -0.79
     estekak
    -0.79
     purpoſe
    -0.79
     houſe
    -0.78
     eſt
    -0.78
     myſelf
    -0.78
     preſent
    -0.78
     Efq
    -0.77
    POSITIVE LOGITS
     enthusiastic
    1.21
     passionately
    1.16
     eagerly
    1.07
     diligently
    1.02
     proudly
    0.99
     ferv
    0.98
     vigorously
    0.98
     confidently
    0.96
     wholeheartedly
    0.96
     intently
    0.96
    Activations Density 0.324%

    No Known Activations