© 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. 16-GEMMASCOPE-RES-16K
    11. 7955
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to engineering and systems analysis

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

    German words and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    thus, if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incentiv
    -1.13
     onboarding
    -1.08
     microbiome
    -1.04
     impactful
    -1.04
     
    -1.02
     curated
    -0.89
     upfront
    -0.88
     nuanced
    -0.85
     prioritise
    -0.84
    qPCR
    -0.84
    POSITIVE LOGITS
     daß
    1.34
     muß
    1.17
     läßt
    1.16
    faßt
    1.14
     mußten
    1.13
     mußte
    1.12
     skall
    1.10
     müßte
    1.02
     Daß
    0.95
    luß
    0.89
    Activations Density 9.810%

    No Known Activations